├── CONTRIBUTING.md ├── LICENSE ├── LLM_CALL.py ├── README.md ├── THIRD_PARTY_NOTICES.md ├── assets ├── HLE_benchmark.png ├── cost_performance.png ├── method.png ├── results.png ├── results_figure.png ├── tool_calling_analysis.png └── toolscale.png ├── data_synthesis ├── prompts │ ├── data_model_prompt.txt │ ├── db_entry_prompt.txt │ ├── evolve_prompt.txt │ ├── schema_prompt.txt │ ├── table_prompt.txt │ ├── task_prompt.txt │ └── tool_prompt.txt └── run.ipynb ├── evaluation ├── .gitattributes ├── data_dir │ └── tau2 │ │ ├── domains │ │ ├── airline │ │ │ ├── db.json │ │ │ ├── original_tasks.json │ │ │ ├── policy.md │ │ │ └── tasks.json │ │ ├── bank │ │ │ ├── db.json │ │ │ └── policy.md │ │ ├── basketball │ │ │ ├── db.json │ │ │ └── policy.md │ │ ├── ecommerce │ │ │ ├── db.json │ │ │ └── policy.md │ │ ├── medicine │ │ │ ├── db.json │ │ │ └── policy.md │ │ ├── mock │ │ │ ├── db.json │ │ │ ├── policy.md │ │ │ ├── policy_solo.md │ │ │ └── tasks.json │ │ ├── movie │ │ │ ├── db.json │ │ │ └── policy.md │ │ ├── railway │ │ │ ├── db.json │ │ │ └── policy.md │ │ ├── restaurant │ │ │ ├── db.json │ │ │ └── policy.md │ │ ├── retail │ │ │ ├── db.json │ │ │ ├── policy.md │ │ │ └── tasks.json │ │ ├── school │ │ │ ├── db.json │ │ │ └── policy.md │ │ ├── telecom │ │ │ ├── db.toml │ │ │ ├── main_policy.md │ │ │ ├── main_policy_solo.md │ │ │ ├── tasks.json │ │ │ ├── tasks_full.json │ │ │ ├── tasks_small.json │ │ │ ├── tech_support_manual.md │ │ │ ├── tech_support_workflow.md │ │ │ ├── tech_support_workflow_solo.md │ │ │ ├── user_db.toml │ │ │ └── workflows │ │ │ │ ├── dot_2_pdf.py │ │ │ │ ├── tech_support_path1_no_service.dot │ │ │ │ ├── tech_support_path1_no_service.pdf │ │ │ │ ├── tech_support_path1_no_service.png │ │ │ │ ├── tech_support_path2_mobile_data.dot │ │ │ │ ├── tech_support_path2_mobile_data.pdf │ │ │ │ ├── tech_support_path2_mobile_data.png │ │ │ │ ├── tech_support_path3_mms.dot │ │ │ │ ├── tech_support_path3_mms.pdf │ │ │ │ └── tech_support_path3_mms.png │ │ ├── travel │ │ │ ├── db.json │ │ │ └── policy.md │ │ └── weather │ │ │ ├── db.json │ │ │ └── policy.md │ │ └── user_simulator │ │ ├── simulation_guidelines.md │ │ └── simulation_guidelines_tools.md ├── eval_frames.py ├── eval_hle.py ├── eval_hle_basic.py ├── examples.json ├── frames.jsonl ├── hle.jsonl ├── retrieval_hle.py ├── retrieval_wiki.py ├── run_frames.py ├── run_hle.py ├── simulation_guidelines.md ├── simulation_guidelines_tools.md ├── tau2-bench │ ├── .env.example │ ├── .python-version │ ├── .vscode │ │ └── settings.json │ ├── LICENSE │ ├── Makefile │ ├── README.md │ ├── config.py │ ├── pdm.lock │ ├── pyproject.toml │ ├── run.py │ ├── scripts │ │ └── start_tau2_server.sh │ ├── tau2 │ │ ├── __init__.py │ │ ├── agent │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── base.py │ │ │ └── llm_agent.py │ │ ├── api_service │ │ │ ├── __init__.py │ │ │ ├── api_config.py │ │ │ ├── data_model.py │ │ │ └── simulation_service.py │ │ ├── cli.py │ │ ├── config.py │ │ ├── data_model │ │ │ ├── __init__.py │ │ │ ├── message.py │ │ │ ├── simulation.py │ │ │ └── tasks.py │ │ ├── domains │ │ │ ├── README.md │ │ │ ├── __init__.py │ │ │ ├── airline │ │ │ │ ├── __init__.py │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ ├── tools.py │ │ │ │ └── utils.py │ │ │ ├── bank │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ └── tools.py │ │ │ ├── basketball │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ └── tools.py │ │ │ ├── ecommerce │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ └── tools.py │ │ │ ├── medicine │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ └── tools.py │ │ │ ├── mock │ │ │ │ ├── __init__.py │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ ├── tools.py │ │ │ │ └── utils.py │ │ │ ├── movie │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ └── tools.py │ │ │ ├── railway │ │ │ │ ├── __init__.py │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ ├── tools.py │ │ │ │ └── utils.py │ │ │ ├── restaurant │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ └── tools.py │ │ │ ├── retail │ │ │ │ ├── __init__.py │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ ├── tools.py │ │ │ │ └── utils.py │ │ │ ├── school │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ └── tools.py │ │ │ ├── telecom │ │ │ │ ├── __init__.py │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ ├── tasks │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── const.py │ │ │ │ │ ├── create_tasks.py │ │ │ │ │ ├── manager.py │ │ │ │ │ ├── mms_issues.py │ │ │ │ │ ├── mobile_data_issues.py │ │ │ │ │ ├── service_issues.py │ │ │ │ │ └── utils.py │ │ │ │ ├── tools.py │ │ │ │ ├── user_data_model.py │ │ │ │ ├── user_tools.py │ │ │ │ └── utils.py │ │ │ ├── travel │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ └── tools.py │ │ │ └── weather │ │ │ │ ├── __init__.py │ │ │ │ ├── data_model.py │ │ │ │ ├── environment.py │ │ │ │ ├── tools.py │ │ │ │ └── utils.py │ │ ├── environment │ │ │ ├── __init__.py │ │ │ ├── db.py │ │ │ ├── environment.py │ │ │ ├── server.py │ │ │ ├── tool.py │ │ │ ├── toolkit.py │ │ │ └── utils │ │ │ │ └── interface_agent.py │ │ ├── evaluator │ │ │ ├── __init__.py │ │ │ ├── evaluator.py │ │ │ ├── evaluator_action.py │ │ │ ├── evaluator_base.py │ │ │ ├── evaluator_communicate.py │ │ │ ├── evaluator_env.py │ │ │ └── evaluator_nl_assertions.py │ │ ├── metrics │ │ │ ├── __init__.py │ │ │ ├── agent_metrics.py │ │ │ └── break_down_metrics.py │ │ ├── orchestrator │ │ │ ├── __init__.py │ │ │ ├── environment_manager.py │ │ │ ├── orchestrator.py │ │ │ └── utils.py │ │ ├── registry.py │ │ ├── run.py │ │ ├── scripts │ │ │ ├── __init__.py │ │ │ ├── show_domain_doc.py │ │ │ ├── start_servers.py │ │ │ └── view_simulations.py │ │ ├── user │ │ │ ├── __init__.py │ │ │ ├── base.py │ │ │ └── user_simulator.py │ │ └── utils │ │ │ ├── __init__.py │ │ │ ├── display.py │ │ │ ├── io_utils.py │ │ │ ├── llm_utils.py │ │ │ ├── pydantic_utils.py │ │ │ └── utils.py │ └── tests │ │ ├── conftest.py │ │ ├── test_agent.py │ │ ├── test_domains │ │ ├── test_airline │ │ │ ├── __init__.py │ │ │ └── test_tools_airline.py │ │ ├── test_mock │ │ │ ├── __init__.py │ │ │ └── test_tools_mock.py │ │ ├── test_retail │ │ │ ├── __init__.py │ │ │ └── test_tools_retail.py │ │ └── test_telecom │ │ │ ├── test_tools_telecom.py │ │ │ └── test_user_tools_telecom.py │ │ ├── test_environment.py │ │ ├── test_llm_utils.py │ │ ├── test_orchestrator.py │ │ ├── test_run.py │ │ ├── test_tasks.py │ │ └── test_user.py ├── tool_chat_template_llama3.1_json.jinja └── tools.json ├── requirements.txt └── training ├── .DS_Store ├── .gitattributes ├── LICENSE ├── Notice.txt ├── data.jsonl ├── docker ├── Apptainerfile.rocm ├── Dockerfile.awsefa ├── Dockerfile.custom ├── Dockerfile.ngc.vllm ├── Dockerfile.ngc.vllm0.8 ├── Dockerfile.ngc.vllm0.8.5 ├── Dockerfile.ngc.vllm0.8.sagemaker ├── Dockerfile.rocm ├── Dockerfile.sglang ├── Dockerfile.vemlp.vllm.te ├── Dockerfile.vllm.sglang.megatron ├── Dockerfile.vllm.sglang.megatron.deepseek └── entrypoint.sh ├── environments.sh ├── examples ├── data_preprocess │ ├── aime2024_multiturn_w_tool.py │ ├── dapo_multiturn_w_tool.py │ ├── full_hh_rlhf.py │ ├── geo3k.py │ ├── gsm8k.py │ ├── gsm8k_multiturn_w_tool.py │ ├── hellaswag.py │ ├── math_dataset.py │ ├── multiturn.py │ └── preprocess_search_r1_dataset.py ├── generation │ ├── run_deepseek7b_mutli_node.sh │ └── run_deepseek_v2_lite_math.sh ├── grpo_trainer │ ├── README.md │ ├── run_deepseek671b_math_megatron.sh │ ├── run_deepseek7b_llm.sh │ ├── run_deepseek7b_llm_math.sh │ ├── run_deepseek7b_llm_math_megatron.sh │ ├── run_deepseek7b_llm_seq_balance.sh │ ├── run_moonlight16b_math_megatron.sh │ ├── run_qwen2-7b.sh │ ├── run_qwen2-7b_math.sh │ ├── run_qwen2-7b_math_megatron.sh │ ├── run_qwen2-7b_seq_balance.sh │ ├── run_qwen2-7b_seq_balance_math_megatron.sh │ ├── run_qwen2-7b_sgl_megatron.sh │ ├── run_qwen2_5-3b_gsm8k_grpo_lora.sh │ ├── run_qwen2_5-7b_math_megatron_diff_tp.sh │ ├── run_qwen2_5_vl-7b.sh │ ├── run_qwen3-236b_megatron.sh │ ├── run_qwen3-8b.sh │ └── run_qwen3moe-30b_megatron.sh ├── ppo_trainer │ ├── README.md │ ├── run_deepseek7b_llm.sh │ ├── run_deepseek7b_llm_modelscope.sh │ ├── run_deepseek7b_llm_pfppo.sh │ ├── run_deepseek7b_llm_sandbox_fusion.sh │ ├── run_deepseek7b_llm_sp2.sh │ ├── run_deepseek_full_hh_rlhf.sh │ ├── run_deepseek_math_gsm8k_megatron.sh │ ├── run_gemma.sh │ ├── run_moonlight16b_a3b_gsm8k_megatron.sh │ ├── run_qwen1.5_moe_a2.7b-gsm8k_megatron.sh │ ├── run_qwen2-7b_math_gsm8k_megatron.sh │ ├── run_qwen2-7b_rm.sh │ ├── run_qwen2-7b_rm_seq_balance.sh │ ├── run_qwen2-7b_seq_balance.sh │ ├── run_qwen2-7b_sglang_seq_balance.sh │ └── run_qwen2.5-32b.sh ├── ray │ └── tutorial.ipynb ├── reinforce_plus_plus_trainer │ ├── run_qwen2-7b_math_rf.sh │ └── run_qwen2-7b_math_rf_baseline.sh ├── remax_trainer │ ├── run_qwen2.5-3b_seq_balance.sh │ └── run_qwen2.5-7b_seq_balance.sh ├── rloo_trainer │ └── run_qwen2-7b.sh ├── sft │ ├── gsm8k │ │ ├── run_deepseek_6b7.sh │ │ ├── run_gemma_2b.sh │ │ ├── run_gemma_7b.sh │ │ ├── run_qwen_05_peft.sh │ │ ├── run_qwen_05_sp2.sh │ │ └── run_qwen_05_sp2_liger.sh │ └── multiturn │ │ └── run_qwen_05_sp2.sh ├── sglang_multiturn │ ├── README.md │ ├── config │ │ ├── gsm8k_multiturn_grpo.yaml │ │ ├── gsm8k_multiturn_megatron_grpo.yaml │ │ ├── retool_multiturn_grpo.yaml │ │ ├── search_multiturn_grpo.yaml │ │ └── tool_config │ │ │ ├── gsm8k_tool_config.yaml │ │ │ ├── sandbox_fusion_tool_config.yaml │ │ │ └── search_tool_config.yaml │ ├── run_qwen2.5-3b_gsm8k_multiturn.sh │ ├── run_qwen2.5-3b_gsm8k_multiturn_4xgpu.sh │ ├── run_qwen2.5-3b_megatron_gsm8k_multiturn.sh │ └── search_r1_like │ │ ├── local_dense_retriever │ │ ├── download.py │ │ └── retrieval_server.py │ │ └── run_qwen2.5-3b_instruct_search_multiturn.sh ├── slurm │ └── ray_on_slurm.slurm ├── split_placement │ ├── README.md │ ├── config │ │ └── ppo_trainer_split.yaml │ ├── main_ppo_split.py │ ├── run_deepseek7b_llm.sh │ └── split_monkey_patch.py └── tuning │ ├── 14b │ └── qwen2_14b_grpo_4_h800_fsdp_vllm.sh │ ├── 32b │ └── qwen2_32B_grpo_8_h20_megatron_vllm.sh │ ├── 70b │ ├── qwen2-70b_grpo_32_h20_fsdp_vllm.sh │ └── qwen2-70b_grpo_32_h800_fsdp_vllm.sh │ └── 7b │ └── qwen2-7b_grpo_2_h800_fsdp_vllm.sh ├── general_thought_example_urls.json ├── launch.sh ├── lead_agent ├── __init__.py └── llm_agent │ ├── __init__.py │ ├── generation_quick3.py │ ├── tensor_helper.py │ └── tools.py ├── pyproject.toml ├── recipe ├── algo │ ├── config │ │ └── grpo_trainer.yaml │ ├── grpo_ray_trainer_quick3.py │ └── main_grpo_quick3.py └── dapo │ ├── README.md │ ├── config │ └── dapo_trainer.yaml │ ├── dapo_ray_trainer.py │ ├── main_dapo.py │ ├── prepare_dapo_data.sh │ ├── run_dapo_early_qwen2.5_32b.sh │ ├── run_dapo_qwen2.5_32b.sh │ ├── run_dapo_wo_ds_qwen2.5_32b.sh │ ├── test_dapo_7b.sh │ ├── test_dapo_7b_math.sh │ ├── test_dapo_7b_math_lora.sh │ ├── test_dapo_7b_math_megatron.sh │ ├── test_dapo_dspk_671b_megatron.sh │ └── test_dapo_qwen3_30b_math.sh ├── requirements-npu.txt ├── requirements.txt ├── requirements_sglang.txt ├── resume_h100.py ├── resume_run_h100.sh ├── retrieval_general_thought.py ├── rollout ├── .env.example ├── .python-version ├── Makefile ├── config.py ├── pdm.lock ├── pyproject.toml └── tau2 │ ├── __init__.py │ ├── agent │ ├── README.md │ ├── __init__.py │ ├── base.py │ └── llm_agent.py │ ├── api_service │ ├── __init__.py │ ├── api_config.py │ ├── data_model.py │ └── simulation_service.py │ ├── cli.py │ ├── config.py │ ├── data_model │ ├── __init__.py │ ├── message.py │ ├── simulation.py │ └── tasks.py │ ├── domains │ ├── README.md │ ├── __init__.py │ ├── airline │ │ ├── __init__.py │ │ ├── data_model.py │ │ ├── environment.py │ │ ├── tools.py │ │ └── utils.py │ ├── bank │ │ ├── data_model.py │ │ ├── environment.py │ │ └── tools.py │ ├── basketball │ │ ├── data_model.py │ │ ├── environment.py │ │ └── tools.py │ ├── ecommerce │ │ ├── data_model.py │ │ ├── environment.py │ │ └── tools.py │ ├── medicine │ │ ├── data_model.py │ │ ├── environment.py │ │ └── tools.py │ ├── mock │ │ ├── __init__.py │ │ ├── data_model.py │ │ ├── environment.py │ │ ├── tools.py │ │ └── utils.py │ ├── movie │ │ ├── data_model.py │ │ ├── environment.py │ │ └── tools.py │ ├── railway │ │ ├── __init__.py │ │ ├── data_model.py │ │ ├── environment.py │ │ ├── tools.py │ │ └── utils.py │ ├── restaurant │ │ ├── data_model.py │ │ ├── environment.py │ │ └── tools.py │ ├── retail │ │ ├── __init__.py │ │ ├── data_model.py │ │ ├── environment.py │ │ ├── tools.py │ │ └── utils.py │ ├── school │ │ ├── data_model.py │ │ ├── environment.py │ │ └── tools.py │ ├── telecom │ │ ├── __init__.py │ │ ├── data_model.py │ │ ├── environment.py │ │ ├── tasks │ │ │ ├── __init__.py │ │ │ ├── const.py │ │ │ ├── create_tasks.py │ │ │ ├── manager.py │ │ │ ├── mms_issues.py │ │ │ ├── mobile_data_issues.py │ │ │ ├── service_issues.py │ │ │ └── utils.py │ │ ├── tools.py │ │ ├── user_data_model.py │ │ ├── user_tools.py │ │ └── utils.py │ ├── travel │ │ ├── data_model.py │ │ ├── environment.py │ │ └── tools.py │ └── weather │ │ ├── __init__.py │ │ ├── data_model.py │ │ ├── environment.py │ │ ├── tools.py │ │ └── utils.py │ ├── environment │ ├── __init__.py │ ├── db.py │ ├── environment.py │ ├── server.py │ ├── tool.py │ ├── toolkit.py │ └── utils │ │ └── interface_agent.py │ ├── evaluator │ ├── __init__.py │ ├── evaluator.py │ ├── evaluator_action.py │ ├── evaluator_base.py │ ├── evaluator_communicate.py │ ├── evaluator_env.py │ └── evaluator_nl_assertions.py │ ├── metrics │ ├── __init__.py │ ├── agent_metrics.py │ └── break_down_metrics.py │ ├── orchestrator │ ├── __init__.py │ ├── environment_manager.py │ ├── orchestrator.py │ └── utils.py │ ├── registry.py │ ├── run.py │ ├── scripts │ ├── __init__.py │ ├── show_domain_doc.py │ ├── start_servers.py │ └── view_simulations.py │ ├── user │ ├── __init__.py │ ├── base.py │ └── user_simulator.py │ └── utils │ ├── __init__.py │ ├── display.py │ ├── io_utils.py │ ├── llm_utils.py │ ├── pydantic_utils.py │ └── utils.py ├── scripts ├── converter_hf_to_mcore.py ├── diagnose.py ├── init_random_model.py ├── install_vllm_sglang_mcore.sh └── model_merger.py ├── se_t4_1.sh ├── se_t4_2.sh ├── se_t4_3.sh ├── setup.py ├── tests ├── __init__.py ├── distributed │ ├── run_all.sh │ └── test_tensor_dict.py ├── gpu_utility │ ├── test_memory_buffers.py │ ├── test_ops.py │ └── test_torch_functional.py ├── kernels │ └── test_linear_cross_entropy.py ├── kill_github_tests.sh ├── models │ ├── test_transformer.py │ └── test_transformers_ulysses.py ├── npu │ ├── run_qwen2_5_05b_dapo.sh │ ├── run_qwen2_5_05b_grpo.sh │ ├── run_qwen2_5_32b_grpo.sh │ └── run_qwen2_5_7b_grpo.sh ├── ray_cpu │ ├── check_worker_alive │ │ └── main.py │ ├── test_auto_padding.py │ ├── test_check_worker_alive.py │ ├── test_decorator.py │ ├── test_fused_workers.py │ ├── test_ray_local_envs.py │ └── test_ray_utils.py ├── ray_gpu │ ├── detached_worker │ │ ├── README.md │ │ ├── client.py │ │ ├── run.sh │ │ └── server.py │ ├── test_colocated_workers.py │ ├── test_colocated_workers_fused.py │ ├── test_data_transfer.py │ ├── test_driverfunc_to_worker.py │ ├── test_high_level_scheduling_api.py │ ├── test_rvdz.py │ ├── test_worker_group_basics.py │ └── test_worker_group_torch.py ├── reward_score │ └── test_sandbox_fusion.py ├── sandbox │ └── test_sandbox.py ├── sanity │ ├── check_license.py │ ├── check_pr_title.py │ ├── test_config_docs.py │ └── test_import.py ├── single_controller │ └── base │ │ └── test_decorator.py ├── test_protocol.py ├── trainer │ ├── __init__.py │ └── ppo │ │ ├── __init__.py │ │ ├── test_core_algos.py │ │ └── test_metric_utils.py ├── utils │ ├── cpu_tests │ │ ├── _test_module.py │ │ ├── test_fs.py │ │ ├── test_import_utils.py │ │ ├── test_model.py │ │ └── test_timeout_decorator.py │ └── gpu_tests │ │ ├── checkpoint │ │ └── test_fsdp_ckpt.py │ │ ├── dataset │ │ ├── test_multiturn_sft_dataset.py │ │ ├── test_rl_dataset.py │ │ ├── test_rm_dataset.py │ │ └── test_sft_dataset.py │ │ ├── megatron │ │ └── test_pipeline_parallel.py │ │ ├── test_activation_offload.py │ │ ├── test_flops_counter.py │ │ ├── test_seqlen_balancing.py │ │ └── test_torch_functional.py └── workers │ ├── reward_manager │ └── test_registry.py │ └── rollout │ ├── async_rollout_utils.py │ ├── resource │ └── tool_configs │ │ ├── sandbox_fusion_tool_config │ │ └── search_tool_config │ ├── run_fsdp_vllm.py │ ├── test_async_sglang_server.py │ ├── test_custom_completion_callback.py │ ├── test_hf_rollout.py │ ├── test_sglang_async_rollout_search_tools.py │ ├── test_sglang_async_rollout_sf_tools.py │ ├── test_sglang_async_rollout_w_tools.py │ ├── test_sglang_spmd.py │ ├── test_vllm_chat_scheduler.py │ ├── test_vllm_hf_loader.py │ ├── test_vllm_spmd.py │ └── utils_sglang.py ├── tool_chat_template_llama3.1_json.jinja ├── tools.json ├── tools_debug.json ├── verl.egg-info ├── PKG-INFO ├── SOURCES.txt ├── dependency_links.txt ├── requires.txt └── top_level.txt └── verl ├── __init__.py ├── models ├── README.md ├── __init__.py ├── llama │ ├── __init__.py │ └── megatron │ │ ├── __init__.py │ │ ├── checkpoint_utils │ │ ├── __init__.py │ │ ├── llama_loader.py │ │ ├── llama_loader_depracated.py │ │ └── llama_saver.py │ │ ├── layers │ │ ├── __init__.py │ │ ├── parallel_attention.py │ │ ├── parallel_decoder.py │ │ ├── parallel_linear.py │ │ ├── parallel_mlp.py │ │ └── parallel_rmsnorm.py │ │ └── modeling_llama_megatron.py ├── mcore │ ├── __init__.py │ ├── config_converter.py │ ├── loader.py │ ├── model_forward.py │ ├── model_initializer.py │ ├── patch_v012.py │ ├── readme.md │ ├── registry.py │ ├── saver.py │ ├── util.py │ └── weight_converter.py ├── qwen2 │ ├── __init__.py │ └── megatron │ │ ├── __init__.py │ │ ├── checkpoint_utils │ │ ├── __init__.py │ │ ├── qwen2_loader.py │ │ ├── qwen2_loader_depracated.py │ │ └── qwen2_saver.py │ │ ├── layers │ │ ├── __init__.py │ │ ├── parallel_attention.py │ │ ├── parallel_decoder.py │ │ ├── parallel_linear.py │ │ ├── parallel_mlp.py │ │ └── parallel_rmsnorm.py │ │ └── modeling_qwen2_megatron.py ├── registry.py ├── transformers │ ├── __init__.py │ ├── kimi_vl.py │ ├── llama.py │ ├── monkey_patch.py │ ├── qwen2.py │ ├── qwen2_5_vl.py │ └── qwen2_vl.py └── weight_loader_registry.py ├── nvidia ├── __init__.py ├── eval │ ├── __init__.py │ ├── deepscaler_eval.yaml │ ├── gen_utils.py │ └── general_eval.py ├── remote_reward_server │ ├── benchmark_remote_reward.py │ ├── launch_default_reward_server.py │ ├── test_local_code_reward.py │ ├── test_local_rllm_code_reward.py │ ├── test_remote_code_reward.py │ └── test_remote_math_reward.py ├── reward_manager │ ├── __init__.py │ ├── length_penalty.py │ ├── naive.py │ └── prime.py ├── reward_score │ ├── __init__.py │ ├── deepcoder │ │ ├── __init__.py │ │ ├── code_reward.py │ │ ├── code_utils │ │ │ ├── codeforces.py │ │ │ ├── firejail_exec.py │ │ │ ├── humanevalplus.py │ │ │ ├── kodcode.py │ │ │ ├── livecodebench.py │ │ │ ├── pyext2.py │ │ │ ├── taco.py │ │ │ └── utils.py │ │ └── reward_types.py │ ├── deepscaler │ │ ├── __init__.py │ │ ├── globals.py │ │ ├── math_reward.py │ │ ├── math_utils │ │ │ ├── __init__.py │ │ │ └── utils.py │ │ └── reward_types.py │ ├── gsm8k.py │ ├── ifeval │ │ ├── __init__.py │ │ ├── evaluation_main.py │ │ ├── instructions.py │ │ ├── instructions_registry.py │ │ └── instructions_util.py │ ├── math.py │ ├── prime_code │ │ ├── __init__.py │ │ ├── testing_util.py │ │ └── utils.py │ ├── prime_math │ │ ├── __init__.py │ │ ├── grader.py │ │ └── math_normalize.py │ └── toolcall │ │ ├── __init__.py │ │ └── toolcall.py ├── scripts │ ├── deepseek_evaluation.sh │ ├── deepseek_reinforce_baseline_dapo.sh │ └── eval_model.sh └── utils │ ├── __init__.py │ ├── timer.py │ └── utils.py ├── protocol.py ├── single_controller ├── __init__.py ├── base │ ├── __init__.py │ ├── decorator.py │ ├── megatron │ │ ├── __init__.py │ │ ├── worker.py │ │ └── worker_group.py │ ├── register_center │ │ ├── __init__.py │ │ └── ray.py │ ├── worker.py │ └── worker_group.py └── ray │ ├── __init__.py │ ├── base.py │ └── megatron.py ├── third_party ├── __init__.py ├── sglang │ ├── __init__.py │ └── parallel_state.py └── vllm │ ├── __init__.py │ ├── vllm_v_0_5_4 │ ├── __init__.py │ ├── arg_utils.py │ ├── config.py │ ├── dtensor_weight_loaders.py │ ├── hf_weight_loader.py │ ├── llm.py │ ├── llm_engine_sp.py │ ├── megatron_weight_loaders.py │ ├── model_loader.py │ ├── model_runner.py │ ├── parallel_state.py │ ├── spmd_gpu_executor.py │ ├── tokenizer.py │ └── worker.py │ └── vllm_v_0_6_3 │ ├── __init__.py │ ├── arg_utils.py │ ├── config.py │ ├── dtensor_weight_loaders.py │ ├── hf_weight_loader.py │ ├── llm.py │ ├── llm_engine_sp.py │ ├── megatron_weight_loaders.py │ ├── model_loader.py │ ├── model_runner.py │ ├── parallel_state.py │ ├── spmd_gpu_executor.py │ ├── tokenizer.py │ └── worker.py ├── tools ├── __init__.py ├── base_tool.py ├── gsm8k_tool.py ├── sandbox_fusion_tools.py ├── schemas.py ├── search_tool.py └── utils │ ├── __init__.py │ └── search_r1_like_utils.py ├── trainer ├── __init__.py ├── config │ ├── evaluation.yaml │ ├── generation.yaml │ ├── ppo_megatron_trainer.yaml │ ├── ppo_trainer.yaml │ └── sft_trainer.yaml ├── fsdp_sft_trainer.py ├── main_eval.py ├── main_generation.py ├── main_ppo.py ├── ppo │ ├── __init__.py │ ├── core_algos.py │ ├── metric_utils.py │ ├── ray_trainer.py │ └── reward.py ├── runtime_env.yaml └── tool_configs │ ├── 0615_1413.json │ └── 0615_1601.json ├── utils ├── __init__.py ├── activation_offload.py ├── checkpoint │ ├── __init__.py │ ├── checkpoint_manager.py │ ├── fsdp_checkpoint_manager.py │ └── megatron_checkpoint_manager.py ├── config.py ├── dataset │ ├── README.md │ ├── __init__.py │ ├── multiturn_sft_dataset.py │ ├── rl_dataset.py │ ├── rm_dataset.py │ ├── sft_dataset.py │ └── vision_utils.py ├── debug │ ├── __init__.py │ ├── performance.py │ ├── profile.py │ └── trajectory_tracker.py ├── device.py ├── distributed.py ├── experimental │ ├── __init__.py │ └── torch_functional.py ├── flops_counter.py ├── fs.py ├── fsdp_utils.py ├── hdfs_io.py ├── import_utils.py ├── logger │ ├── __init__.py │ └── aggregate_logger.py ├── logging_utils.py ├── megatron │ ├── __init__.py │ ├── memory.py │ ├── optimizer.py │ ├── pipeline_parallel.py │ ├── sequence_parallel.py │ └── tensor_parallel.py ├── megatron_utils.py ├── memory_buffer.py ├── metric │ ├── __init__.py │ └── utils.py ├── model.py ├── net_utils.py ├── py_functional.py ├── ray_utils.py ├── rendezvous │ ├── __init__.py │ └── ray_backend.py ├── reward_score │ ├── __init__.py │ ├── geo3k.py │ ├── gsm8k.py │ ├── math.py │ ├── math_batch.py │ ├── math_dapo.py │ ├── math_verify.py │ ├── prime_code │ │ ├── __init__.py │ │ ├── testing_util.py │ │ └── utils.py │ ├── prime_math │ │ ├── __init__.py │ │ ├── grader.py │ │ └── math_normalize.py │ ├── sandbox_fusion │ │ ├── __init__.py │ │ └── utils.py │ └── search_r1_like_qa_em.py ├── seqlen_balancing.py ├── tokenizer.py ├── torch_dtypes.py ├── torch_functional.py ├── tracking.py ├── ulysses.py └── vllm_utils.py ├── version └── version └── workers ├── __init__.py ├── actor ├── __init__.py ├── base.py ├── dp_actor.py └── megatron_actor.py ├── critic ├── __init__.py ├── base.py ├── dp_critic.py └── megatron_critic.py ├── fsdp_workers.py ├── megatron_workers.py ├── reward_manager ├── __init__.py ├── batch.py ├── dapo.py ├── naive.py ├── prime.py └── registry.py ├── reward_model ├── __init__.py ├── base.py └── megatron │ ├── __init__.py │ └── reward_model.py ├── rollout ├── __init__.py ├── async_server.py ├── base.py ├── chat_scheduler.py ├── hf_rollout.py ├── naive │ ├── __init__.py │ └── naive_rollout.py ├── schemas.py ├── sglang_rollout │ ├── __init__.py │ ├── async_sglang_server.py │ ├── sglang_rollout.py │ └── utils.py ├── tokenizer.py └── vllm_rollout │ ├── __init__.py │ ├── fire_vllm_rollout.py │ ├── vllm_async_server.py │ ├── vllm_rollout.py │ └── vllm_rollout_spmd.py └── sharding_manager ├── __init__.py ├── base.py ├── fsdp_sglang.py ├── fsdp_ulysses.py ├── fsdp_vllm.py ├── megatron_sglang.py └── megatron_vllm.py /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/LICENSE -------------------------------------------------------------------------------- /LLM_CALL.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/LLM_CALL.py -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/README.md -------------------------------------------------------------------------------- /THIRD_PARTY_NOTICES.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/THIRD_PARTY_NOTICES.md -------------------------------------------------------------------------------- /assets/HLE_benchmark.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/assets/HLE_benchmark.png -------------------------------------------------------------------------------- /assets/cost_performance.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/assets/cost_performance.png -------------------------------------------------------------------------------- /assets/method.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/assets/method.png -------------------------------------------------------------------------------- /assets/results.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/assets/results.png -------------------------------------------------------------------------------- /assets/results_figure.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/assets/results_figure.png -------------------------------------------------------------------------------- /assets/tool_calling_analysis.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/assets/tool_calling_analysis.png -------------------------------------------------------------------------------- /assets/toolscale.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/assets/toolscale.png -------------------------------------------------------------------------------- /data_synthesis/prompts/data_model_prompt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/data_synthesis/prompts/data_model_prompt.txt -------------------------------------------------------------------------------- /data_synthesis/prompts/db_entry_prompt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/data_synthesis/prompts/db_entry_prompt.txt -------------------------------------------------------------------------------- /data_synthesis/prompts/evolve_prompt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/data_synthesis/prompts/evolve_prompt.txt -------------------------------------------------------------------------------- /data_synthesis/prompts/schema_prompt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/data_synthesis/prompts/schema_prompt.txt -------------------------------------------------------------------------------- /data_synthesis/prompts/table_prompt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/data_synthesis/prompts/table_prompt.txt -------------------------------------------------------------------------------- /data_synthesis/prompts/task_prompt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/data_synthesis/prompts/task_prompt.txt -------------------------------------------------------------------------------- /data_synthesis/prompts/tool_prompt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/data_synthesis/prompts/tool_prompt.txt -------------------------------------------------------------------------------- /data_synthesis/run.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/data_synthesis/run.ipynb -------------------------------------------------------------------------------- /evaluation/.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/.gitattributes -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/airline/db.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/airline/db.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/airline/original_tasks.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/airline/original_tasks.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/airline/policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/airline/policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/airline/tasks.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/airline/tasks.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/bank/db.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/bank/db.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/bank/policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/bank/policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/basketball/db.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/basketball/db.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/basketball/policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/basketball/policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/ecommerce/db.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/ecommerce/db.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/ecommerce/policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/ecommerce/policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/medicine/db.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/medicine/db.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/medicine/policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/medicine/policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/mock/db.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/mock/db.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/mock/policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/mock/policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/mock/policy_solo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/mock/policy_solo.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/mock/tasks.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/mock/tasks.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/movie/db.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/movie/db.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/movie/policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/movie/policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/railway/db.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/railway/db.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/railway/policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/railway/policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/restaurant/db.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/restaurant/db.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/restaurant/policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/restaurant/policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/retail/db.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/retail/db.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/retail/policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/retail/policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/retail/tasks.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/retail/tasks.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/school/db.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/school/db.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/school/policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/school/policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/telecom/db.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/telecom/db.toml -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/telecom/main_policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/telecom/main_policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/telecom/main_policy_solo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/telecom/main_policy_solo.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/telecom/tasks.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/telecom/tasks.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/telecom/tasks_full.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/telecom/tasks_full.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/telecom/tasks_small.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/telecom/tasks_small.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/telecom/tech_support_manual.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/telecom/tech_support_manual.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/telecom/tech_support_workflow.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/telecom/tech_support_workflow.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/telecom/user_db.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/telecom/user_db.toml -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/telecom/workflows/dot_2_pdf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/telecom/workflows/dot_2_pdf.py -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/travel/db.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/travel/db.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/travel/policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/travel/policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/weather/db.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/weather/db.json -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/domains/weather/policy.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/domains/weather/policy.md -------------------------------------------------------------------------------- /evaluation/data_dir/tau2/user_simulator/simulation_guidelines.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/data_dir/tau2/user_simulator/simulation_guidelines.md -------------------------------------------------------------------------------- /evaluation/eval_frames.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/eval_frames.py -------------------------------------------------------------------------------- /evaluation/eval_hle.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/eval_hle.py -------------------------------------------------------------------------------- /evaluation/eval_hle_basic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/eval_hle_basic.py -------------------------------------------------------------------------------- /evaluation/examples.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/examples.json -------------------------------------------------------------------------------- /evaluation/frames.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/frames.jsonl -------------------------------------------------------------------------------- /evaluation/hle.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/hle.jsonl -------------------------------------------------------------------------------- /evaluation/retrieval_hle.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/retrieval_hle.py -------------------------------------------------------------------------------- /evaluation/retrieval_wiki.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/retrieval_wiki.py -------------------------------------------------------------------------------- /evaluation/run_frames.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/run_frames.py -------------------------------------------------------------------------------- /evaluation/run_hle.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/run_hle.py -------------------------------------------------------------------------------- /evaluation/simulation_guidelines.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/simulation_guidelines.md -------------------------------------------------------------------------------- /evaluation/simulation_guidelines_tools.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/simulation_guidelines_tools.md -------------------------------------------------------------------------------- /evaluation/tau2-bench/.env.example: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/.env.example -------------------------------------------------------------------------------- /evaluation/tau2-bench/.python-version: -------------------------------------------------------------------------------- 1 | 3.13 2 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/.vscode/settings.json: -------------------------------------------------------------------------------- 1 | { 2 | "git.ignoreLimitWarning": true 3 | } -------------------------------------------------------------------------------- /evaluation/tau2-bench/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/LICENSE -------------------------------------------------------------------------------- /evaluation/tau2-bench/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/Makefile -------------------------------------------------------------------------------- /evaluation/tau2-bench/README.md: -------------------------------------------------------------------------------- 1 | tau2-ben eval 2 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/config.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/pdm.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/pdm.lock -------------------------------------------------------------------------------- /evaluation/tau2-bench/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/pyproject.toml -------------------------------------------------------------------------------- /evaluation/tau2-bench/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/run.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/scripts/start_tau2_server.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/scripts/start_tau2_server.sh -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/agent/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/agent/README.md -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/agent/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/agent/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/agent/base.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/agent/llm_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/agent/llm_agent.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/api_service/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright Sierra 2 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/api_service/api_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/api_service/api_config.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/api_service/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/api_service/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/api_service/simulation_service.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/api_service/simulation_service.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/cli.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/config.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/data_model/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/data_model/message.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/data_model/message.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/data_model/simulation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/data_model/simulation.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/data_model/tasks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/data_model/tasks.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/README.md -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/airline/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright Sierra 2 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/airline/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/airline/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/airline/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/airline/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/airline/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/airline/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/airline/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/airline/utils.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/bank/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/bank/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/bank/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/bank/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/bank/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/bank/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/basketball/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/basketball/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/basketball/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/basketball/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/basketball/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/basketball/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/ecommerce/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/ecommerce/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/ecommerce/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/ecommerce/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/ecommerce/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/ecommerce/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/medicine/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/medicine/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/medicine/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/medicine/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/medicine/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/medicine/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/mock/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright Sierra 2 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/mock/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/mock/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/mock/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/mock/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/mock/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/mock/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/mock/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/mock/utils.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/movie/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/movie/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/movie/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/movie/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/movie/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/movie/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/railway/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright Sierra 2 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/railway/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/railway/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/railway/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/railway/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/railway/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/railway/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/railway/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/railway/utils.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/restaurant/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/restaurant/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/restaurant/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/restaurant/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/restaurant/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/restaurant/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/retail/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright Sierra 2 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/retail/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/retail/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/retail/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/retail/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/retail/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/retail/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/retail/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/retail/utils.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/school/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/school/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/school/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/school/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/school/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/school/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright Sierra 2 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/telecom/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/telecom/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/tasks/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/tasks/const.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/telecom/tasks/const.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/tasks/create_tasks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/telecom/tasks/create_tasks.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/tasks/manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/telecom/tasks/manager.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/tasks/mms_issues.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/telecom/tasks/mms_issues.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/tasks/service_issues.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/telecom/tasks/service_issues.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/tasks/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/telecom/tasks/utils.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/telecom/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/user_data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/telecom/user_data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/user_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/telecom/user_tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/telecom/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/telecom/utils.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/travel/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/travel/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/travel/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/travel/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/travel/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/travel/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/weather/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright Sierra 2 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/weather/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/weather/data_model.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/weather/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/weather/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/weather/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/weather/tools.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/domains/weather/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/domains/weather/utils.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/environment/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/environment/db.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/environment/db.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/environment/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/environment/environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/environment/server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/environment/server.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/environment/tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/environment/tool.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/environment/toolkit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/environment/toolkit.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/environment/utils/interface_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/environment/utils/interface_agent.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/evaluator/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/evaluator/evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/evaluator/evaluator.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/evaluator/evaluator_action.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/evaluator/evaluator_action.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/evaluator/evaluator_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/evaluator/evaluator_base.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/evaluator/evaluator_communicate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/evaluator/evaluator_communicate.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/evaluator/evaluator_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/evaluator/evaluator_env.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/evaluator/evaluator_nl_assertions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/evaluator/evaluator_nl_assertions.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/metrics/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/metrics/agent_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/metrics/agent_metrics.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/metrics/break_down_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/metrics/break_down_metrics.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/orchestrator/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/orchestrator/environment_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/orchestrator/environment_manager.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/orchestrator/orchestrator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/orchestrator/orchestrator.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/orchestrator/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/orchestrator/utils.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/registry.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/run.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/scripts/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/scripts/show_domain_doc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/scripts/show_domain_doc.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/scripts/start_servers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/scripts/start_servers.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/scripts/view_simulations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/scripts/view_simulations.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/user/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/user/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/user/base.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/user/user_simulator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/user/user_simulator.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/utils/__init__.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/utils/display.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/utils/display.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/utils/io_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/utils/io_utils.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/utils/llm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/utils/llm_utils.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/utils/pydantic_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/utils/pydantic_utils.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tau2/utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tau2/utils/utils.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tests/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tests/conftest.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tests/test_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tests/test_agent.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tests/test_domains/test_airline/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tests/test_domains/test_mock/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tests/test_domains/test_retail/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /evaluation/tau2-bench/tests/test_environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tests/test_environment.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tests/test_llm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tests/test_llm_utils.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tests/test_orchestrator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tests/test_orchestrator.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tests/test_run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tests/test_run.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tests/test_tasks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tests/test_tasks.py -------------------------------------------------------------------------------- /evaluation/tau2-bench/tests/test_user.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tau2-bench/tests/test_user.py -------------------------------------------------------------------------------- /evaluation/tool_chat_template_llama3.1_json.jinja: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tool_chat_template_llama3.1_json.jinja -------------------------------------------------------------------------------- /evaluation/tools.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/evaluation/tools.json -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/requirements.txt -------------------------------------------------------------------------------- /training/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/.DS_Store -------------------------------------------------------------------------------- /training/.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/.gitattributes -------------------------------------------------------------------------------- /training/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/LICENSE -------------------------------------------------------------------------------- /training/Notice.txt: -------------------------------------------------------------------------------- 1 | Copyright 2023-2024 Bytedance Ltd. and/or its affiliates -------------------------------------------------------------------------------- /training/data.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/data.jsonl -------------------------------------------------------------------------------- /training/docker/Apptainerfile.rocm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/docker/Apptainerfile.rocm -------------------------------------------------------------------------------- /training/docker/Dockerfile.awsefa: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/docker/Dockerfile.awsefa -------------------------------------------------------------------------------- /training/docker/Dockerfile.custom: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/docker/Dockerfile.custom -------------------------------------------------------------------------------- /training/docker/Dockerfile.ngc.vllm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/docker/Dockerfile.ngc.vllm -------------------------------------------------------------------------------- /training/docker/Dockerfile.ngc.vllm0.8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/docker/Dockerfile.ngc.vllm0.8 -------------------------------------------------------------------------------- /training/docker/Dockerfile.ngc.vllm0.8.5: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/docker/Dockerfile.ngc.vllm0.8.5 -------------------------------------------------------------------------------- /training/docker/Dockerfile.ngc.vllm0.8.sagemaker: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/docker/Dockerfile.ngc.vllm0.8.sagemaker -------------------------------------------------------------------------------- /training/docker/Dockerfile.rocm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/docker/Dockerfile.rocm -------------------------------------------------------------------------------- /training/docker/Dockerfile.sglang: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/docker/Dockerfile.sglang -------------------------------------------------------------------------------- /training/docker/Dockerfile.vemlp.vllm.te: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/docker/Dockerfile.vemlp.vllm.te -------------------------------------------------------------------------------- /training/docker/Dockerfile.vllm.sglang.megatron: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/docker/Dockerfile.vllm.sglang.megatron -------------------------------------------------------------------------------- /training/docker/Dockerfile.vllm.sglang.megatron.deepseek: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/docker/Dockerfile.vllm.sglang.megatron.deepseek -------------------------------------------------------------------------------- /training/docker/entrypoint.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/docker/entrypoint.sh -------------------------------------------------------------------------------- /training/environments.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/environments.sh -------------------------------------------------------------------------------- /training/examples/data_preprocess/aime2024_multiturn_w_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/data_preprocess/aime2024_multiturn_w_tool.py -------------------------------------------------------------------------------- /training/examples/data_preprocess/dapo_multiturn_w_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/data_preprocess/dapo_multiturn_w_tool.py -------------------------------------------------------------------------------- /training/examples/data_preprocess/full_hh_rlhf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/data_preprocess/full_hh_rlhf.py -------------------------------------------------------------------------------- /training/examples/data_preprocess/geo3k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/data_preprocess/geo3k.py -------------------------------------------------------------------------------- /training/examples/data_preprocess/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/data_preprocess/gsm8k.py -------------------------------------------------------------------------------- /training/examples/data_preprocess/gsm8k_multiturn_w_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/data_preprocess/gsm8k_multiturn_w_tool.py -------------------------------------------------------------------------------- /training/examples/data_preprocess/hellaswag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/data_preprocess/hellaswag.py -------------------------------------------------------------------------------- /training/examples/data_preprocess/math_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/data_preprocess/math_dataset.py -------------------------------------------------------------------------------- /training/examples/data_preprocess/multiturn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/data_preprocess/multiturn.py -------------------------------------------------------------------------------- /training/examples/data_preprocess/preprocess_search_r1_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/data_preprocess/preprocess_search_r1_dataset.py -------------------------------------------------------------------------------- /training/examples/generation/run_deepseek7b_mutli_node.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/generation/run_deepseek7b_mutli_node.sh -------------------------------------------------------------------------------- /training/examples/generation/run_deepseek_v2_lite_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/generation/run_deepseek_v2_lite_math.sh -------------------------------------------------------------------------------- /training/examples/grpo_trainer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/grpo_trainer/README.md -------------------------------------------------------------------------------- /training/examples/grpo_trainer/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/grpo_trainer/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /training/examples/grpo_trainer/run_deepseek7b_llm_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/grpo_trainer/run_deepseek7b_llm_math.sh -------------------------------------------------------------------------------- /training/examples/grpo_trainer/run_qwen2-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/grpo_trainer/run_qwen2-7b.sh -------------------------------------------------------------------------------- /training/examples/grpo_trainer/run_qwen2-7b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/grpo_trainer/run_qwen2-7b_math.sh -------------------------------------------------------------------------------- /training/examples/grpo_trainer/run_qwen2-7b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/grpo_trainer/run_qwen2-7b_math_megatron.sh -------------------------------------------------------------------------------- /training/examples/grpo_trainer/run_qwen2-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/grpo_trainer/run_qwen2-7b_seq_balance.sh -------------------------------------------------------------------------------- /training/examples/grpo_trainer/run_qwen2-7b_sgl_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/grpo_trainer/run_qwen2-7b_sgl_megatron.sh -------------------------------------------------------------------------------- /training/examples/grpo_trainer/run_qwen2_5_vl-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/grpo_trainer/run_qwen2_5_vl-7b.sh -------------------------------------------------------------------------------- /training/examples/grpo_trainer/run_qwen3-236b_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/grpo_trainer/run_qwen3-236b_megatron.sh -------------------------------------------------------------------------------- /training/examples/grpo_trainer/run_qwen3-8b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/grpo_trainer/run_qwen3-8b.sh -------------------------------------------------------------------------------- /training/examples/grpo_trainer/run_qwen3moe-30b_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/grpo_trainer/run_qwen3moe-30b_megatron.sh -------------------------------------------------------------------------------- /training/examples/ppo_trainer/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/ppo_trainer/README.md -------------------------------------------------------------------------------- /training/examples/ppo_trainer/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/ppo_trainer/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /training/examples/ppo_trainer/run_deepseek7b_llm_modelscope.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/ppo_trainer/run_deepseek7b_llm_modelscope.sh -------------------------------------------------------------------------------- /training/examples/ppo_trainer/run_deepseek7b_llm_pfppo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/ppo_trainer/run_deepseek7b_llm_pfppo.sh -------------------------------------------------------------------------------- /training/examples/ppo_trainer/run_deepseek7b_llm_sp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/ppo_trainer/run_deepseek7b_llm_sp2.sh -------------------------------------------------------------------------------- /training/examples/ppo_trainer/run_deepseek_full_hh_rlhf.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/ppo_trainer/run_deepseek_full_hh_rlhf.sh -------------------------------------------------------------------------------- /training/examples/ppo_trainer/run_gemma.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/ppo_trainer/run_gemma.sh -------------------------------------------------------------------------------- /training/examples/ppo_trainer/run_qwen2-7b_rm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/ppo_trainer/run_qwen2-7b_rm.sh -------------------------------------------------------------------------------- /training/examples/ppo_trainer/run_qwen2-7b_rm_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/ppo_trainer/run_qwen2-7b_rm_seq_balance.sh -------------------------------------------------------------------------------- /training/examples/ppo_trainer/run_qwen2-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/ppo_trainer/run_qwen2-7b_seq_balance.sh -------------------------------------------------------------------------------- /training/examples/ppo_trainer/run_qwen2.5-32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/ppo_trainer/run_qwen2.5-32b.sh -------------------------------------------------------------------------------- /training/examples/ray/tutorial.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/ray/tutorial.ipynb -------------------------------------------------------------------------------- /training/examples/remax_trainer/run_qwen2.5-3b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/remax_trainer/run_qwen2.5-3b_seq_balance.sh -------------------------------------------------------------------------------- /training/examples/remax_trainer/run_qwen2.5-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/remax_trainer/run_qwen2.5-7b_seq_balance.sh -------------------------------------------------------------------------------- /training/examples/rloo_trainer/run_qwen2-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/rloo_trainer/run_qwen2-7b.sh -------------------------------------------------------------------------------- /training/examples/sft/gsm8k/run_deepseek_6b7.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/sft/gsm8k/run_deepseek_6b7.sh -------------------------------------------------------------------------------- /training/examples/sft/gsm8k/run_gemma_2b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/sft/gsm8k/run_gemma_2b.sh -------------------------------------------------------------------------------- /training/examples/sft/gsm8k/run_gemma_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/sft/gsm8k/run_gemma_7b.sh -------------------------------------------------------------------------------- /training/examples/sft/gsm8k/run_qwen_05_peft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/sft/gsm8k/run_qwen_05_peft.sh -------------------------------------------------------------------------------- /training/examples/sft/gsm8k/run_qwen_05_sp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/sft/gsm8k/run_qwen_05_sp2.sh -------------------------------------------------------------------------------- /training/examples/sft/gsm8k/run_qwen_05_sp2_liger.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/sft/gsm8k/run_qwen_05_sp2_liger.sh -------------------------------------------------------------------------------- /training/examples/sft/multiturn/run_qwen_05_sp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/sft/multiturn/run_qwen_05_sp2.sh -------------------------------------------------------------------------------- /training/examples/sglang_multiturn/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/sglang_multiturn/README.md -------------------------------------------------------------------------------- /training/examples/slurm/ray_on_slurm.slurm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/slurm/ray_on_slurm.slurm -------------------------------------------------------------------------------- /training/examples/split_placement/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/split_placement/README.md -------------------------------------------------------------------------------- /training/examples/split_placement/config/ppo_trainer_split.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/split_placement/config/ppo_trainer_split.yaml -------------------------------------------------------------------------------- /training/examples/split_placement/main_ppo_split.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/split_placement/main_ppo_split.py -------------------------------------------------------------------------------- /training/examples/split_placement/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/split_placement/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /training/examples/split_placement/split_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/split_placement/split_monkey_patch.py -------------------------------------------------------------------------------- /training/examples/tuning/14b/qwen2_14b_grpo_4_h800_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/tuning/14b/qwen2_14b_grpo_4_h800_fsdp_vllm.sh -------------------------------------------------------------------------------- /training/examples/tuning/70b/qwen2-70b_grpo_32_h20_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/tuning/70b/qwen2-70b_grpo_32_h20_fsdp_vllm.sh -------------------------------------------------------------------------------- /training/examples/tuning/7b/qwen2-7b_grpo_2_h800_fsdp_vllm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/examples/tuning/7b/qwen2-7b_grpo_2_h800_fsdp_vllm.sh -------------------------------------------------------------------------------- /training/general_thought_example_urls.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/general_thought_example_urls.json -------------------------------------------------------------------------------- /training/launch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/launch.sh -------------------------------------------------------------------------------- /training/lead_agent/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/lead_agent/__init__.py -------------------------------------------------------------------------------- /training/lead_agent/llm_agent/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/lead_agent/llm_agent/__init__.py -------------------------------------------------------------------------------- /training/lead_agent/llm_agent/generation_quick3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/lead_agent/llm_agent/generation_quick3.py -------------------------------------------------------------------------------- /training/lead_agent/llm_agent/tensor_helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/lead_agent/llm_agent/tensor_helper.py -------------------------------------------------------------------------------- /training/lead_agent/llm_agent/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/lead_agent/llm_agent/tools.py -------------------------------------------------------------------------------- /training/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/pyproject.toml -------------------------------------------------------------------------------- /training/recipe/algo/config/grpo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/algo/config/grpo_trainer.yaml -------------------------------------------------------------------------------- /training/recipe/algo/grpo_ray_trainer_quick3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/algo/grpo_ray_trainer_quick3.py -------------------------------------------------------------------------------- /training/recipe/algo/main_grpo_quick3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/algo/main_grpo_quick3.py -------------------------------------------------------------------------------- /training/recipe/dapo/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/README.md -------------------------------------------------------------------------------- /training/recipe/dapo/config/dapo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/config/dapo_trainer.yaml -------------------------------------------------------------------------------- /training/recipe/dapo/dapo_ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/dapo_ray_trainer.py -------------------------------------------------------------------------------- /training/recipe/dapo/main_dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/main_dapo.py -------------------------------------------------------------------------------- /training/recipe/dapo/prepare_dapo_data.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/prepare_dapo_data.sh -------------------------------------------------------------------------------- /training/recipe/dapo/run_dapo_early_qwen2.5_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/run_dapo_early_qwen2.5_32b.sh -------------------------------------------------------------------------------- /training/recipe/dapo/run_dapo_qwen2.5_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/run_dapo_qwen2.5_32b.sh -------------------------------------------------------------------------------- /training/recipe/dapo/run_dapo_wo_ds_qwen2.5_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/run_dapo_wo_ds_qwen2.5_32b.sh -------------------------------------------------------------------------------- /training/recipe/dapo/test_dapo_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/test_dapo_7b.sh -------------------------------------------------------------------------------- /training/recipe/dapo/test_dapo_7b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/test_dapo_7b_math.sh -------------------------------------------------------------------------------- /training/recipe/dapo/test_dapo_7b_math_lora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/test_dapo_7b_math_lora.sh -------------------------------------------------------------------------------- /training/recipe/dapo/test_dapo_7b_math_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/test_dapo_7b_math_megatron.sh -------------------------------------------------------------------------------- /training/recipe/dapo/test_dapo_dspk_671b_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/test_dapo_dspk_671b_megatron.sh -------------------------------------------------------------------------------- /training/recipe/dapo/test_dapo_qwen3_30b_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/recipe/dapo/test_dapo_qwen3_30b_math.sh -------------------------------------------------------------------------------- /training/requirements-npu.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/requirements-npu.txt -------------------------------------------------------------------------------- /training/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/requirements.txt -------------------------------------------------------------------------------- /training/requirements_sglang.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/requirements_sglang.txt -------------------------------------------------------------------------------- /training/resume_h100.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/resume_h100.py -------------------------------------------------------------------------------- /training/resume_run_h100.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/resume_run_h100.sh -------------------------------------------------------------------------------- /training/retrieval_general_thought.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/retrieval_general_thought.py -------------------------------------------------------------------------------- /training/rollout/.env.example: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/.env.example -------------------------------------------------------------------------------- /training/rollout/.python-version: -------------------------------------------------------------------------------- 1 | 3.13 2 | -------------------------------------------------------------------------------- /training/rollout/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/Makefile -------------------------------------------------------------------------------- /training/rollout/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/config.py -------------------------------------------------------------------------------- /training/rollout/pdm.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/pdm.lock -------------------------------------------------------------------------------- /training/rollout/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/pyproject.toml -------------------------------------------------------------------------------- /training/rollout/tau2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/agent/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/agent/README.md -------------------------------------------------------------------------------- /training/rollout/tau2/agent/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/agent/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/agent/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/agent/base.py -------------------------------------------------------------------------------- /training/rollout/tau2/agent/llm_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/agent/llm_agent.py -------------------------------------------------------------------------------- /training/rollout/tau2/api_service/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/api_service/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/api_service/api_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/api_service/api_config.py -------------------------------------------------------------------------------- /training/rollout/tau2/api_service/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/api_service/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/api_service/simulation_service.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/api_service/simulation_service.py -------------------------------------------------------------------------------- /training/rollout/tau2/cli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/cli.py -------------------------------------------------------------------------------- /training/rollout/tau2/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/config.py -------------------------------------------------------------------------------- /training/rollout/tau2/data_model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/data_model/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/data_model/message.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/data_model/message.py -------------------------------------------------------------------------------- /training/rollout/tau2/data_model/simulation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/data_model/simulation.py -------------------------------------------------------------------------------- /training/rollout/tau2/data_model/tasks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/data_model/tasks.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/README.md -------------------------------------------------------------------------------- /training/rollout/tau2/domains/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/airline/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/airline/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/airline/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/airline/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/airline/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/airline/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/airline/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/airline/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/airline/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/airline/utils.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/bank/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/bank/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/bank/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/bank/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/bank/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/bank/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/basketball/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/basketball/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/basketball/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/basketball/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/basketball/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/basketball/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/ecommerce/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/ecommerce/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/ecommerce/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/ecommerce/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/ecommerce/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/ecommerce/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/medicine/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/medicine/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/medicine/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/medicine/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/medicine/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/medicine/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/mock/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/mock/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/mock/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/mock/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/mock/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/mock/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/mock/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/mock/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/mock/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/mock/utils.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/movie/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/movie/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/movie/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/movie/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/movie/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/movie/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/railway/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/railway/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/railway/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/railway/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/railway/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/railway/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/railway/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/railway/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/railway/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/railway/utils.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/restaurant/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/restaurant/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/restaurant/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/restaurant/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/restaurant/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/restaurant/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/retail/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/retail/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/retail/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/retail/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/retail/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/retail/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/retail/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/retail/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/retail/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/retail/utils.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/school/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/school/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/school/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/school/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/school/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/school/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/tasks/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/tasks/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/tasks/const.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/tasks/const.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/tasks/create_tasks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/tasks/create_tasks.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/tasks/manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/tasks/manager.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/tasks/mms_issues.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/tasks/mms_issues.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/tasks/service_issues.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/tasks/service_issues.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/tasks/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/tasks/utils.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/user_data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/user_data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/user_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/user_tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/telecom/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/telecom/utils.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/travel/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/travel/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/travel/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/travel/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/travel/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/travel/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/weather/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/weather/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/weather/data_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/weather/data_model.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/weather/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/weather/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/weather/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/weather/tools.py -------------------------------------------------------------------------------- /training/rollout/tau2/domains/weather/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/domains/weather/utils.py -------------------------------------------------------------------------------- /training/rollout/tau2/environment/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/environment/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/environment/db.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/environment/db.py -------------------------------------------------------------------------------- /training/rollout/tau2/environment/environment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/environment/environment.py -------------------------------------------------------------------------------- /training/rollout/tau2/environment/server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/environment/server.py -------------------------------------------------------------------------------- /training/rollout/tau2/environment/tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/environment/tool.py -------------------------------------------------------------------------------- /training/rollout/tau2/environment/toolkit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/environment/toolkit.py -------------------------------------------------------------------------------- /training/rollout/tau2/environment/utils/interface_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/environment/utils/interface_agent.py -------------------------------------------------------------------------------- /training/rollout/tau2/evaluator/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/evaluator/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/evaluator/evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/evaluator/evaluator.py -------------------------------------------------------------------------------- /training/rollout/tau2/evaluator/evaluator_action.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/evaluator/evaluator_action.py -------------------------------------------------------------------------------- /training/rollout/tau2/evaluator/evaluator_base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/evaluator/evaluator_base.py -------------------------------------------------------------------------------- /training/rollout/tau2/evaluator/evaluator_communicate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/evaluator/evaluator_communicate.py -------------------------------------------------------------------------------- /training/rollout/tau2/evaluator/evaluator_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/evaluator/evaluator_env.py -------------------------------------------------------------------------------- /training/rollout/tau2/evaluator/evaluator_nl_assertions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/evaluator/evaluator_nl_assertions.py -------------------------------------------------------------------------------- /training/rollout/tau2/metrics/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/metrics/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/metrics/agent_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/metrics/agent_metrics.py -------------------------------------------------------------------------------- /training/rollout/tau2/metrics/break_down_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/metrics/break_down_metrics.py -------------------------------------------------------------------------------- /training/rollout/tau2/orchestrator/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/orchestrator/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/orchestrator/environment_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/orchestrator/environment_manager.py -------------------------------------------------------------------------------- /training/rollout/tau2/orchestrator/orchestrator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/orchestrator/orchestrator.py -------------------------------------------------------------------------------- /training/rollout/tau2/orchestrator/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/orchestrator/utils.py -------------------------------------------------------------------------------- /training/rollout/tau2/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/registry.py -------------------------------------------------------------------------------- /training/rollout/tau2/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/run.py -------------------------------------------------------------------------------- /training/rollout/tau2/scripts/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/scripts/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/scripts/show_domain_doc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/scripts/show_domain_doc.py -------------------------------------------------------------------------------- /training/rollout/tau2/scripts/start_servers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/scripts/start_servers.py -------------------------------------------------------------------------------- /training/rollout/tau2/scripts/view_simulations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/scripts/view_simulations.py -------------------------------------------------------------------------------- /training/rollout/tau2/user/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/user/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/user/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/user/base.py -------------------------------------------------------------------------------- /training/rollout/tau2/user/user_simulator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/user/user_simulator.py -------------------------------------------------------------------------------- /training/rollout/tau2/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/utils/__init__.py -------------------------------------------------------------------------------- /training/rollout/tau2/utils/display.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/utils/display.py -------------------------------------------------------------------------------- /training/rollout/tau2/utils/io_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/utils/io_utils.py -------------------------------------------------------------------------------- /training/rollout/tau2/utils/llm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/utils/llm_utils.py -------------------------------------------------------------------------------- /training/rollout/tau2/utils/pydantic_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/utils/pydantic_utils.py -------------------------------------------------------------------------------- /training/rollout/tau2/utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/rollout/tau2/utils/utils.py -------------------------------------------------------------------------------- /training/scripts/converter_hf_to_mcore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/scripts/converter_hf_to_mcore.py -------------------------------------------------------------------------------- /training/scripts/diagnose.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/scripts/diagnose.py -------------------------------------------------------------------------------- /training/scripts/init_random_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/scripts/init_random_model.py -------------------------------------------------------------------------------- /training/scripts/install_vllm_sglang_mcore.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/scripts/install_vllm_sglang_mcore.sh -------------------------------------------------------------------------------- /training/scripts/model_merger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/scripts/model_merger.py -------------------------------------------------------------------------------- /training/se_t4_1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/se_t4_1.sh -------------------------------------------------------------------------------- /training/se_t4_2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/se_t4_2.sh -------------------------------------------------------------------------------- /training/se_t4_3.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/se_t4_3.sh -------------------------------------------------------------------------------- /training/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/setup.py -------------------------------------------------------------------------------- /training/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/__init__.py -------------------------------------------------------------------------------- /training/tests/distributed/run_all.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/distributed/run_all.sh -------------------------------------------------------------------------------- /training/tests/distributed/test_tensor_dict.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/distributed/test_tensor_dict.py -------------------------------------------------------------------------------- /training/tests/gpu_utility/test_memory_buffers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/gpu_utility/test_memory_buffers.py -------------------------------------------------------------------------------- /training/tests/gpu_utility/test_ops.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/gpu_utility/test_ops.py -------------------------------------------------------------------------------- /training/tests/gpu_utility/test_torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/gpu_utility/test_torch_functional.py -------------------------------------------------------------------------------- /training/tests/kernels/test_linear_cross_entropy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/kernels/test_linear_cross_entropy.py -------------------------------------------------------------------------------- /training/tests/kill_github_tests.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/kill_github_tests.sh -------------------------------------------------------------------------------- /training/tests/models/test_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/models/test_transformer.py -------------------------------------------------------------------------------- /training/tests/models/test_transformers_ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/models/test_transformers_ulysses.py -------------------------------------------------------------------------------- /training/tests/npu/run_qwen2_5_05b_dapo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/npu/run_qwen2_5_05b_dapo.sh -------------------------------------------------------------------------------- /training/tests/npu/run_qwen2_5_05b_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/npu/run_qwen2_5_05b_grpo.sh -------------------------------------------------------------------------------- /training/tests/npu/run_qwen2_5_32b_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/npu/run_qwen2_5_32b_grpo.sh -------------------------------------------------------------------------------- /training/tests/npu/run_qwen2_5_7b_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/npu/run_qwen2_5_7b_grpo.sh -------------------------------------------------------------------------------- /training/tests/ray_cpu/check_worker_alive/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_cpu/check_worker_alive/main.py -------------------------------------------------------------------------------- /training/tests/ray_cpu/test_auto_padding.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_cpu/test_auto_padding.py -------------------------------------------------------------------------------- /training/tests/ray_cpu/test_check_worker_alive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_cpu/test_check_worker_alive.py -------------------------------------------------------------------------------- /training/tests/ray_cpu/test_decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_cpu/test_decorator.py -------------------------------------------------------------------------------- /training/tests/ray_cpu/test_fused_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_cpu/test_fused_workers.py -------------------------------------------------------------------------------- /training/tests/ray_cpu/test_ray_local_envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_cpu/test_ray_local_envs.py -------------------------------------------------------------------------------- /training/tests/ray_cpu/test_ray_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_cpu/test_ray_utils.py -------------------------------------------------------------------------------- /training/tests/ray_gpu/detached_worker/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_gpu/detached_worker/README.md -------------------------------------------------------------------------------- /training/tests/ray_gpu/detached_worker/client.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_gpu/detached_worker/client.py -------------------------------------------------------------------------------- /training/tests/ray_gpu/detached_worker/run.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_gpu/detached_worker/run.sh -------------------------------------------------------------------------------- /training/tests/ray_gpu/detached_worker/server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_gpu/detached_worker/server.py -------------------------------------------------------------------------------- /training/tests/ray_gpu/test_colocated_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_gpu/test_colocated_workers.py -------------------------------------------------------------------------------- /training/tests/ray_gpu/test_colocated_workers_fused.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_gpu/test_colocated_workers_fused.py -------------------------------------------------------------------------------- /training/tests/ray_gpu/test_data_transfer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_gpu/test_data_transfer.py -------------------------------------------------------------------------------- /training/tests/ray_gpu/test_driverfunc_to_worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_gpu/test_driverfunc_to_worker.py -------------------------------------------------------------------------------- /training/tests/ray_gpu/test_high_level_scheduling_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_gpu/test_high_level_scheduling_api.py -------------------------------------------------------------------------------- /training/tests/ray_gpu/test_rvdz.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_gpu/test_rvdz.py -------------------------------------------------------------------------------- /training/tests/ray_gpu/test_worker_group_basics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_gpu/test_worker_group_basics.py -------------------------------------------------------------------------------- /training/tests/ray_gpu/test_worker_group_torch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/ray_gpu/test_worker_group_torch.py -------------------------------------------------------------------------------- /training/tests/reward_score/test_sandbox_fusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/reward_score/test_sandbox_fusion.py -------------------------------------------------------------------------------- /training/tests/sandbox/test_sandbox.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/sandbox/test_sandbox.py -------------------------------------------------------------------------------- /training/tests/sanity/check_license.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/sanity/check_license.py -------------------------------------------------------------------------------- /training/tests/sanity/check_pr_title.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/sanity/check_pr_title.py -------------------------------------------------------------------------------- /training/tests/sanity/test_config_docs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/sanity/test_config_docs.py -------------------------------------------------------------------------------- /training/tests/sanity/test_import.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/sanity/test_import.py -------------------------------------------------------------------------------- /training/tests/single_controller/base/test_decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/single_controller/base/test_decorator.py -------------------------------------------------------------------------------- /training/tests/test_protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/test_protocol.py -------------------------------------------------------------------------------- /training/tests/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/trainer/__init__.py -------------------------------------------------------------------------------- /training/tests/trainer/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/trainer/ppo/__init__.py -------------------------------------------------------------------------------- /training/tests/trainer/ppo/test_core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/trainer/ppo/test_core_algos.py -------------------------------------------------------------------------------- /training/tests/trainer/ppo/test_metric_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/trainer/ppo/test_metric_utils.py -------------------------------------------------------------------------------- /training/tests/utils/cpu_tests/_test_module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/utils/cpu_tests/_test_module.py -------------------------------------------------------------------------------- /training/tests/utils/cpu_tests/test_fs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/utils/cpu_tests/test_fs.py -------------------------------------------------------------------------------- /training/tests/utils/cpu_tests/test_import_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/utils/cpu_tests/test_import_utils.py -------------------------------------------------------------------------------- /training/tests/utils/cpu_tests/test_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/utils/cpu_tests/test_model.py -------------------------------------------------------------------------------- /training/tests/utils/cpu_tests/test_timeout_decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/utils/cpu_tests/test_timeout_decorator.py -------------------------------------------------------------------------------- /training/tests/utils/gpu_tests/checkpoint/test_fsdp_ckpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/utils/gpu_tests/checkpoint/test_fsdp_ckpt.py -------------------------------------------------------------------------------- /training/tests/utils/gpu_tests/dataset/test_rl_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/utils/gpu_tests/dataset/test_rl_dataset.py -------------------------------------------------------------------------------- /training/tests/utils/gpu_tests/dataset/test_rm_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/utils/gpu_tests/dataset/test_rm_dataset.py -------------------------------------------------------------------------------- /training/tests/utils/gpu_tests/dataset/test_sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/utils/gpu_tests/dataset/test_sft_dataset.py -------------------------------------------------------------------------------- /training/tests/utils/gpu_tests/test_activation_offload.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/utils/gpu_tests/test_activation_offload.py -------------------------------------------------------------------------------- /training/tests/utils/gpu_tests/test_flops_counter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/utils/gpu_tests/test_flops_counter.py -------------------------------------------------------------------------------- /training/tests/utils/gpu_tests/test_seqlen_balancing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/utils/gpu_tests/test_seqlen_balancing.py -------------------------------------------------------------------------------- /training/tests/utils/gpu_tests/test_torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/utils/gpu_tests/test_torch_functional.py -------------------------------------------------------------------------------- /training/tests/workers/reward_manager/test_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/workers/reward_manager/test_registry.py -------------------------------------------------------------------------------- /training/tests/workers/rollout/async_rollout_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/workers/rollout/async_rollout_utils.py -------------------------------------------------------------------------------- /training/tests/workers/rollout/run_fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/workers/rollout/run_fsdp_vllm.py -------------------------------------------------------------------------------- /training/tests/workers/rollout/test_async_sglang_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/workers/rollout/test_async_sglang_server.py -------------------------------------------------------------------------------- /training/tests/workers/rollout/test_hf_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/workers/rollout/test_hf_rollout.py -------------------------------------------------------------------------------- /training/tests/workers/rollout/test_sglang_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/workers/rollout/test_sglang_spmd.py -------------------------------------------------------------------------------- /training/tests/workers/rollout/test_vllm_chat_scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/workers/rollout/test_vllm_chat_scheduler.py -------------------------------------------------------------------------------- /training/tests/workers/rollout/test_vllm_hf_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/workers/rollout/test_vllm_hf_loader.py -------------------------------------------------------------------------------- /training/tests/workers/rollout/test_vllm_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/workers/rollout/test_vllm_spmd.py -------------------------------------------------------------------------------- /training/tests/workers/rollout/utils_sglang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tests/workers/rollout/utils_sglang.py -------------------------------------------------------------------------------- /training/tool_chat_template_llama3.1_json.jinja: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tool_chat_template_llama3.1_json.jinja -------------------------------------------------------------------------------- /training/tools.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tools.json -------------------------------------------------------------------------------- /training/tools_debug.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/tools_debug.json -------------------------------------------------------------------------------- /training/verl.egg-info/PKG-INFO: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl.egg-info/PKG-INFO -------------------------------------------------------------------------------- /training/verl.egg-info/SOURCES.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl.egg-info/SOURCES.txt -------------------------------------------------------------------------------- /training/verl.egg-info/dependency_links.txt: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /training/verl.egg-info/requires.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl.egg-info/requires.txt -------------------------------------------------------------------------------- /training/verl.egg-info/top_level.txt: -------------------------------------------------------------------------------- 1 | tests 2 | verl 3 | -------------------------------------------------------------------------------- /training/verl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/__init__.py -------------------------------------------------------------------------------- /training/verl/models/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/README.md -------------------------------------------------------------------------------- /training/verl/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/__init__.py -------------------------------------------------------------------------------- /training/verl/models/llama/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/llama/__init__.py -------------------------------------------------------------------------------- /training/verl/models/llama/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/llama/megatron/__init__.py -------------------------------------------------------------------------------- /training/verl/models/llama/megatron/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/llama/megatron/layers/__init__.py -------------------------------------------------------------------------------- /training/verl/models/llama/megatron/layers/parallel_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/llama/megatron/layers/parallel_decoder.py -------------------------------------------------------------------------------- /training/verl/models/llama/megatron/layers/parallel_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/llama/megatron/layers/parallel_linear.py -------------------------------------------------------------------------------- /training/verl/models/llama/megatron/layers/parallel_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/llama/megatron/layers/parallel_mlp.py -------------------------------------------------------------------------------- /training/verl/models/llama/megatron/layers/parallel_rmsnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/llama/megatron/layers/parallel_rmsnorm.py -------------------------------------------------------------------------------- /training/verl/models/llama/megatron/modeling_llama_megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/llama/megatron/modeling_llama_megatron.py -------------------------------------------------------------------------------- /training/verl/models/mcore/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/mcore/__init__.py -------------------------------------------------------------------------------- /training/verl/models/mcore/config_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/mcore/config_converter.py -------------------------------------------------------------------------------- /training/verl/models/mcore/loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/mcore/loader.py -------------------------------------------------------------------------------- /training/verl/models/mcore/model_forward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/mcore/model_forward.py -------------------------------------------------------------------------------- /training/verl/models/mcore/model_initializer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/mcore/model_initializer.py -------------------------------------------------------------------------------- /training/verl/models/mcore/patch_v012.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/mcore/patch_v012.py -------------------------------------------------------------------------------- /training/verl/models/mcore/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/mcore/readme.md -------------------------------------------------------------------------------- /training/verl/models/mcore/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/mcore/registry.py -------------------------------------------------------------------------------- /training/verl/models/mcore/saver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/mcore/saver.py -------------------------------------------------------------------------------- /training/verl/models/mcore/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/mcore/util.py -------------------------------------------------------------------------------- /training/verl/models/mcore/weight_converter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/mcore/weight_converter.py -------------------------------------------------------------------------------- /training/verl/models/qwen2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/qwen2/__init__.py -------------------------------------------------------------------------------- /training/verl/models/qwen2/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/qwen2/megatron/__init__.py -------------------------------------------------------------------------------- /training/verl/models/qwen2/megatron/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/qwen2/megatron/layers/__init__.py -------------------------------------------------------------------------------- /training/verl/models/qwen2/megatron/layers/parallel_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/qwen2/megatron/layers/parallel_decoder.py -------------------------------------------------------------------------------- /training/verl/models/qwen2/megatron/layers/parallel_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/qwen2/megatron/layers/parallel_linear.py -------------------------------------------------------------------------------- /training/verl/models/qwen2/megatron/layers/parallel_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/qwen2/megatron/layers/parallel_mlp.py -------------------------------------------------------------------------------- /training/verl/models/qwen2/megatron/layers/parallel_rmsnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/qwen2/megatron/layers/parallel_rmsnorm.py -------------------------------------------------------------------------------- /training/verl/models/qwen2/megatron/modeling_qwen2_megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/qwen2/megatron/modeling_qwen2_megatron.py -------------------------------------------------------------------------------- /training/verl/models/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/registry.py -------------------------------------------------------------------------------- /training/verl/models/transformers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/transformers/__init__.py -------------------------------------------------------------------------------- /training/verl/models/transformers/kimi_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/transformers/kimi_vl.py -------------------------------------------------------------------------------- /training/verl/models/transformers/llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/transformers/llama.py -------------------------------------------------------------------------------- /training/verl/models/transformers/monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/transformers/monkey_patch.py -------------------------------------------------------------------------------- /training/verl/models/transformers/qwen2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/transformers/qwen2.py -------------------------------------------------------------------------------- /training/verl/models/transformers/qwen2_5_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/transformers/qwen2_5_vl.py -------------------------------------------------------------------------------- /training/verl/models/transformers/qwen2_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/transformers/qwen2_vl.py -------------------------------------------------------------------------------- /training/verl/models/weight_loader_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/models/weight_loader_registry.py -------------------------------------------------------------------------------- /training/verl/nvidia/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/__init__.py -------------------------------------------------------------------------------- /training/verl/nvidia/eval/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/eval/__init__.py -------------------------------------------------------------------------------- /training/verl/nvidia/eval/deepscaler_eval.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/eval/deepscaler_eval.yaml -------------------------------------------------------------------------------- /training/verl/nvidia/eval/gen_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/eval/gen_utils.py -------------------------------------------------------------------------------- /training/verl/nvidia/eval/general_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/eval/general_eval.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_manager/__init__.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_manager/length_penalty.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_manager/length_penalty.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_manager/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_manager/naive.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_manager/prime.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_manager/prime.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/__init__.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/deepcoder/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/deepcoder/__init__.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/deepcoder/code_reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/deepcoder/code_reward.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/deepcoder/code_utils/taco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/deepcoder/code_utils/taco.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/deepcoder/code_utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/deepcoder/code_utils/utils.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/deepcoder/reward_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/deepcoder/reward_types.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/deepscaler/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/deepscaler/__init__.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/deepscaler/globals.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/deepscaler/globals.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/deepscaler/math_reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/deepscaler/math_reward.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/deepscaler/reward_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/deepscaler/reward_types.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/gsm8k.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/ifeval/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/ifeval/__init__.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/ifeval/evaluation_main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/ifeval/evaluation_main.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/ifeval/instructions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/ifeval/instructions.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/ifeval/instructions_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/ifeval/instructions_util.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/math.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/prime_code/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/prime_code/__init__.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/prime_code/testing_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/prime_code/testing_util.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/prime_code/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/prime_code/utils.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/prime_math/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/prime_math/__init__.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/prime_math/grader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/prime_math/grader.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/prime_math/math_normalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/prime_math/math_normalize.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/toolcall/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/toolcall/__init__.py -------------------------------------------------------------------------------- /training/verl/nvidia/reward_score/toolcall/toolcall.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/reward_score/toolcall/toolcall.py -------------------------------------------------------------------------------- /training/verl/nvidia/scripts/deepseek_evaluation.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/scripts/deepseek_evaluation.sh -------------------------------------------------------------------------------- /training/verl/nvidia/scripts/eval_model.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/scripts/eval_model.sh -------------------------------------------------------------------------------- /training/verl/nvidia/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/utils/__init__.py -------------------------------------------------------------------------------- /training/verl/nvidia/utils/timer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/utils/timer.py -------------------------------------------------------------------------------- /training/verl/nvidia/utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/nvidia/utils/utils.py -------------------------------------------------------------------------------- /training/verl/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/protocol.py -------------------------------------------------------------------------------- /training/verl/single_controller/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/single_controller/__init__.py -------------------------------------------------------------------------------- /training/verl/single_controller/base/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/single_controller/base/__init__.py -------------------------------------------------------------------------------- /training/verl/single_controller/base/decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/single_controller/base/decorator.py -------------------------------------------------------------------------------- /training/verl/single_controller/base/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/single_controller/base/megatron/__init__.py -------------------------------------------------------------------------------- /training/verl/single_controller/base/megatron/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/single_controller/base/megatron/worker.py -------------------------------------------------------------------------------- /training/verl/single_controller/base/megatron/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/single_controller/base/megatron/worker_group.py -------------------------------------------------------------------------------- /training/verl/single_controller/base/register_center/ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/single_controller/base/register_center/ray.py -------------------------------------------------------------------------------- /training/verl/single_controller/base/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/single_controller/base/worker.py -------------------------------------------------------------------------------- /training/verl/single_controller/base/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/single_controller/base/worker_group.py -------------------------------------------------------------------------------- /training/verl/single_controller/ray/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/single_controller/ray/__init__.py -------------------------------------------------------------------------------- /training/verl/single_controller/ray/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/single_controller/ray/base.py -------------------------------------------------------------------------------- /training/verl/single_controller/ray/megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/single_controller/ray/megatron.py -------------------------------------------------------------------------------- /training/verl/third_party/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/__init__.py -------------------------------------------------------------------------------- /training/verl/third_party/sglang/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/sglang/__init__.py -------------------------------------------------------------------------------- /training/verl/third_party/sglang/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/sglang/parallel_state.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/__init__.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_5_4/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_5_4/__init__.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_5_4/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_5_4/arg_utils.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_5_4/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_5_4/config.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_5_4/hf_weight_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_5_4/hf_weight_loader.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_5_4/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_5_4/llm.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_5_4/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_5_4/model_runner.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_5_4/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_5_4/worker.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_6_3/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_6_3/__init__.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_6_3/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_6_3/config.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_6_3/hf_weight_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_6_3/hf_weight_loader.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_6_3/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_6_3/llm.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_6_3/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_6_3/model_runner.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_6_3/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_6_3/tokenizer.py -------------------------------------------------------------------------------- /training/verl/third_party/vllm/vllm_v_0_6_3/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/third_party/vllm/vllm_v_0_6_3/worker.py -------------------------------------------------------------------------------- /training/verl/tools/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/tools/__init__.py -------------------------------------------------------------------------------- /training/verl/tools/base_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/tools/base_tool.py -------------------------------------------------------------------------------- /training/verl/tools/gsm8k_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/tools/gsm8k_tool.py -------------------------------------------------------------------------------- /training/verl/tools/sandbox_fusion_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/tools/sandbox_fusion_tools.py -------------------------------------------------------------------------------- /training/verl/tools/schemas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/tools/schemas.py -------------------------------------------------------------------------------- /training/verl/tools/search_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/tools/search_tool.py -------------------------------------------------------------------------------- /training/verl/tools/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/tools/utils/__init__.py -------------------------------------------------------------------------------- /training/verl/tools/utils/search_r1_like_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/tools/utils/search_r1_like_utils.py -------------------------------------------------------------------------------- /training/verl/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/__init__.py -------------------------------------------------------------------------------- /training/verl/trainer/config/evaluation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/config/evaluation.yaml -------------------------------------------------------------------------------- /training/verl/trainer/config/generation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/config/generation.yaml -------------------------------------------------------------------------------- /training/verl/trainer/config/ppo_megatron_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/config/ppo_megatron_trainer.yaml -------------------------------------------------------------------------------- /training/verl/trainer/config/ppo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/config/ppo_trainer.yaml -------------------------------------------------------------------------------- /training/verl/trainer/config/sft_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/config/sft_trainer.yaml -------------------------------------------------------------------------------- /training/verl/trainer/fsdp_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/fsdp_sft_trainer.py -------------------------------------------------------------------------------- /training/verl/trainer/main_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/main_eval.py -------------------------------------------------------------------------------- /training/verl/trainer/main_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/main_generation.py -------------------------------------------------------------------------------- /training/verl/trainer/main_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/main_ppo.py -------------------------------------------------------------------------------- /training/verl/trainer/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/ppo/__init__.py -------------------------------------------------------------------------------- /training/verl/trainer/ppo/core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/ppo/core_algos.py -------------------------------------------------------------------------------- /training/verl/trainer/ppo/metric_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/ppo/metric_utils.py -------------------------------------------------------------------------------- /training/verl/trainer/ppo/ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/ppo/ray_trainer.py -------------------------------------------------------------------------------- /training/verl/trainer/ppo/reward.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/ppo/reward.py -------------------------------------------------------------------------------- /training/verl/trainer/runtime_env.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/runtime_env.yaml -------------------------------------------------------------------------------- /training/verl/trainer/tool_configs/0615_1413.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/tool_configs/0615_1413.json -------------------------------------------------------------------------------- /training/verl/trainer/tool_configs/0615_1601.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/trainer/tool_configs/0615_1601.json -------------------------------------------------------------------------------- /training/verl/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/__init__.py -------------------------------------------------------------------------------- /training/verl/utils/activation_offload.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/activation_offload.py -------------------------------------------------------------------------------- /training/verl/utils/checkpoint/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/checkpoint/__init__.py -------------------------------------------------------------------------------- /training/verl/utils/checkpoint/checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/checkpoint/checkpoint_manager.py -------------------------------------------------------------------------------- /training/verl/utils/checkpoint/fsdp_checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/checkpoint/fsdp_checkpoint_manager.py -------------------------------------------------------------------------------- /training/verl/utils/checkpoint/megatron_checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/checkpoint/megatron_checkpoint_manager.py -------------------------------------------------------------------------------- /training/verl/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/config.py -------------------------------------------------------------------------------- /training/verl/utils/dataset/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/dataset/README.md -------------------------------------------------------------------------------- /training/verl/utils/dataset/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/dataset/__init__.py -------------------------------------------------------------------------------- /training/verl/utils/dataset/multiturn_sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/dataset/multiturn_sft_dataset.py -------------------------------------------------------------------------------- /training/verl/utils/dataset/rl_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/dataset/rl_dataset.py -------------------------------------------------------------------------------- /training/verl/utils/dataset/rm_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/dataset/rm_dataset.py -------------------------------------------------------------------------------- /training/verl/utils/dataset/sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/dataset/sft_dataset.py -------------------------------------------------------------------------------- /training/verl/utils/dataset/vision_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/dataset/vision_utils.py -------------------------------------------------------------------------------- /training/verl/utils/debug/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/debug/__init__.py -------------------------------------------------------------------------------- /training/verl/utils/debug/performance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/debug/performance.py -------------------------------------------------------------------------------- /training/verl/utils/debug/profile.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/debug/profile.py -------------------------------------------------------------------------------- /training/verl/utils/debug/trajectory_tracker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/debug/trajectory_tracker.py -------------------------------------------------------------------------------- /training/verl/utils/device.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/device.py -------------------------------------------------------------------------------- /training/verl/utils/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/distributed.py -------------------------------------------------------------------------------- /training/verl/utils/experimental/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/experimental/__init__.py -------------------------------------------------------------------------------- /training/verl/utils/experimental/torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/experimental/torch_functional.py -------------------------------------------------------------------------------- /training/verl/utils/flops_counter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/flops_counter.py -------------------------------------------------------------------------------- /training/verl/utils/fs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/fs.py -------------------------------------------------------------------------------- /training/verl/utils/fsdp_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/fsdp_utils.py -------------------------------------------------------------------------------- /training/verl/utils/hdfs_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/hdfs_io.py -------------------------------------------------------------------------------- /training/verl/utils/import_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/import_utils.py -------------------------------------------------------------------------------- /training/verl/utils/logger/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/logger/__init__.py -------------------------------------------------------------------------------- /training/verl/utils/logger/aggregate_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/logger/aggregate_logger.py -------------------------------------------------------------------------------- /training/verl/utils/logging_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/logging_utils.py -------------------------------------------------------------------------------- /training/verl/utils/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/megatron/__init__.py -------------------------------------------------------------------------------- /training/verl/utils/megatron/memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/megatron/memory.py -------------------------------------------------------------------------------- /training/verl/utils/megatron/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/megatron/optimizer.py -------------------------------------------------------------------------------- /training/verl/utils/megatron/pipeline_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/megatron/pipeline_parallel.py -------------------------------------------------------------------------------- /training/verl/utils/megatron/sequence_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/megatron/sequence_parallel.py -------------------------------------------------------------------------------- /training/verl/utils/megatron/tensor_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/megatron/tensor_parallel.py -------------------------------------------------------------------------------- /training/verl/utils/megatron_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/megatron_utils.py -------------------------------------------------------------------------------- /training/verl/utils/memory_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/memory_buffer.py -------------------------------------------------------------------------------- /training/verl/utils/metric/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/metric/__init__.py -------------------------------------------------------------------------------- /training/verl/utils/metric/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/metric/utils.py -------------------------------------------------------------------------------- /training/verl/utils/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/model.py -------------------------------------------------------------------------------- /training/verl/utils/net_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/net_utils.py -------------------------------------------------------------------------------- /training/verl/utils/py_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/py_functional.py -------------------------------------------------------------------------------- /training/verl/utils/ray_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/ray_utils.py -------------------------------------------------------------------------------- /training/verl/utils/rendezvous/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/rendezvous/__init__.py -------------------------------------------------------------------------------- /training/verl/utils/rendezvous/ray_backend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/rendezvous/ray_backend.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/__init__.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/geo3k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/geo3k.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/gsm8k.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/math.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/math_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/math_batch.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/math_dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/math_dapo.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/math_verify.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/math_verify.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/prime_code/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/prime_code/__init__.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/prime_code/testing_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/prime_code/testing_util.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/prime_code/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/prime_code/utils.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/prime_math/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/prime_math/__init__.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/prime_math/grader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/prime_math/grader.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/prime_math/math_normalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/prime_math/math_normalize.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/sandbox_fusion/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/sandbox_fusion/__init__.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/sandbox_fusion/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/sandbox_fusion/utils.py -------------------------------------------------------------------------------- /training/verl/utils/reward_score/search_r1_like_qa_em.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/reward_score/search_r1_like_qa_em.py -------------------------------------------------------------------------------- /training/verl/utils/seqlen_balancing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/seqlen_balancing.py -------------------------------------------------------------------------------- /training/verl/utils/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/tokenizer.py -------------------------------------------------------------------------------- /training/verl/utils/torch_dtypes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/torch_dtypes.py -------------------------------------------------------------------------------- /training/verl/utils/torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/torch_functional.py -------------------------------------------------------------------------------- /training/verl/utils/tracking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/tracking.py -------------------------------------------------------------------------------- /training/verl/utils/ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/ulysses.py -------------------------------------------------------------------------------- /training/verl/utils/vllm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/utils/vllm_utils.py -------------------------------------------------------------------------------- /training/verl/version/version: -------------------------------------------------------------------------------- 1 | 0.4.0.dev 2 | -------------------------------------------------------------------------------- /training/verl/workers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/__init__.py -------------------------------------------------------------------------------- /training/verl/workers/actor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/actor/__init__.py -------------------------------------------------------------------------------- /training/verl/workers/actor/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/actor/base.py -------------------------------------------------------------------------------- /training/verl/workers/actor/dp_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/actor/dp_actor.py -------------------------------------------------------------------------------- /training/verl/workers/actor/megatron_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/actor/megatron_actor.py -------------------------------------------------------------------------------- /training/verl/workers/critic/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/critic/__init__.py -------------------------------------------------------------------------------- /training/verl/workers/critic/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/critic/base.py -------------------------------------------------------------------------------- /training/verl/workers/critic/dp_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/critic/dp_critic.py -------------------------------------------------------------------------------- /training/verl/workers/critic/megatron_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/critic/megatron_critic.py -------------------------------------------------------------------------------- /training/verl/workers/fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/fsdp_workers.py -------------------------------------------------------------------------------- /training/verl/workers/megatron_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/megatron_workers.py -------------------------------------------------------------------------------- /training/verl/workers/reward_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/reward_manager/__init__.py -------------------------------------------------------------------------------- /training/verl/workers/reward_manager/batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/reward_manager/batch.py -------------------------------------------------------------------------------- /training/verl/workers/reward_manager/dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/reward_manager/dapo.py -------------------------------------------------------------------------------- /training/verl/workers/reward_manager/naive.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/reward_manager/naive.py -------------------------------------------------------------------------------- /training/verl/workers/reward_manager/prime.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/reward_manager/prime.py -------------------------------------------------------------------------------- /training/verl/workers/reward_manager/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/reward_manager/registry.py -------------------------------------------------------------------------------- /training/verl/workers/reward_model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/reward_model/__init__.py -------------------------------------------------------------------------------- /training/verl/workers/reward_model/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/reward_model/base.py -------------------------------------------------------------------------------- /training/verl/workers/reward_model/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/reward_model/megatron/__init__.py -------------------------------------------------------------------------------- /training/verl/workers/reward_model/megatron/reward_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/reward_model/megatron/reward_model.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/__init__.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/async_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/async_server.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/base.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/chat_scheduler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/chat_scheduler.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/hf_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/hf_rollout.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/naive/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/naive/__init__.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/naive/naive_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/naive/naive_rollout.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/schemas.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/schemas.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/sglang_rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/sglang_rollout/__init__.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/sglang_rollout/sglang_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/sglang_rollout/sglang_rollout.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/sglang_rollout/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/sglang_rollout/utils.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/tokenizer.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/vllm_rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/vllm_rollout/__init__.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/vllm_rollout/fire_vllm_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/vllm_rollout/fire_vllm_rollout.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/vllm_rollout/vllm_async_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/vllm_rollout/vllm_async_server.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/vllm_rollout/vllm_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/vllm_rollout/vllm_rollout.py -------------------------------------------------------------------------------- /training/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/rollout/vllm_rollout/vllm_rollout_spmd.py -------------------------------------------------------------------------------- /training/verl/workers/sharding_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/sharding_manager/__init__.py -------------------------------------------------------------------------------- /training/verl/workers/sharding_manager/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/sharding_manager/base.py -------------------------------------------------------------------------------- /training/verl/workers/sharding_manager/fsdp_sglang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/sharding_manager/fsdp_sglang.py -------------------------------------------------------------------------------- /training/verl/workers/sharding_manager/fsdp_ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/sharding_manager/fsdp_ulysses.py -------------------------------------------------------------------------------- /training/verl/workers/sharding_manager/fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/sharding_manager/fsdp_vllm.py -------------------------------------------------------------------------------- /training/verl/workers/sharding_manager/megatron_sglang.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/sharding_manager/megatron_sglang.py -------------------------------------------------------------------------------- /training/verl/workers/sharding_manager/megatron_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/NVlabs/ToolOrchestra/HEAD/training/verl/workers/sharding_manager/megatron_vllm.py --------------------------------------------------------------------------------