├── LICENSE ├── Notice.txt ├── README.md ├── README_Search-R1.md ├── VERL_README.md ├── download_corpus.sh ├── evaluate.sh ├── evaluate_all.sh ├── infer.py ├── make_ikea.sh ├── pyproject.toml ├── requirements.txt ├── retrieval_launch.sh ├── retrieval_log.txt ├── scripts ├── data_process │ ├── 2wiki_knowledge_boundary.py │ ├── nq.py │ ├── nq_hotpotqa_knowledge_boundary.py │ ├── nq_hotpotqa_knowledge_boundary_easy.py │ ├── nq_hotpotqa_knowledge_boundary_hard.py │ ├── nq_knowledge_boundary.py │ ├── nq_rag.py │ ├── nq_search.py │ └── nq_vanilla.py ├── download.py ├── download.sh ├── e5_Flat.index ├── nq_hotpotqa │ ├── README.md │ ├── evaluate.sh │ ├── train_grpo.sh │ └── train_ppo.sh ├── upload.py └── upload.sh ├── search_r1 ├── __init__.py ├── __pycache__ │ └── __init__.cpython-39.pyc ├── llm_agent │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── generation.cpython-39.pyc │ │ └── tensor_helper.cpython-39.pyc │ ├── generation.py │ └── tensor_helper.py └── search │ ├── build_index.sh │ ├── index_builder.py │ ├── retrieval.py │ ├── retrieval.sh │ ├── retrieval_request.py │ └── retrieval_server.py ├── setup.py ├── sft ├── deepspeed_zero3.yaml ├── main_train_sft.py └── run_train_sft.sh ├── train_grpo_kb.sh ├── train_grpo_vanilla.sh └── verl ├── __init__.py ├── __pycache__ ├── __init__.cpython-310.pyc ├── __init__.cpython-312.pyc ├── __init__.cpython-39.pyc ├── protocol.cpython-310.pyc ├── protocol.cpython-312.pyc └── protocol.cpython-39.pyc ├── models ├── README.md ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-39.pyc │ └── registry.cpython-39.pyc ├── llama │ ├── __init__.py │ └── megatron │ │ ├── __init__.py │ │ ├── checkpoint_utils │ │ ├── __init__.py │ │ ├── llama_loader.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 ├── registry.py ├── transformers │ ├── __init__.py │ ├── llama.py │ ├── monkey_patch.py │ └── qwen2.py └── weight_loader_registry.py ├── protocol.py ├── single_controller ├── __init__.py ├── __pycache__ │ └── __init__.cpython-39.pyc ├── base │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── decorator.cpython-39.pyc │ │ ├── worker.cpython-39.pyc │ │ └── worker_group.cpython-39.pyc │ ├── decorator.py │ ├── megatron │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-39.pyc │ │ │ ├── worker.cpython-39.pyc │ │ │ └── worker_group.cpython-39.pyc │ │ ├── worker.py │ │ └── worker_group.py │ ├── register_center │ │ ├── __init__.py │ │ ├── __pycache__ │ │ │ ├── __init__.cpython-39.pyc │ │ │ └── ray.cpython-39.pyc │ │ └── ray.py │ ├── worker.py │ └── worker_group.py ├── ray │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── base.cpython-39.pyc │ │ └── megatron.cpython-39.pyc │ ├── base.py │ └── megatron.py └── version │ └── version ├── third_party ├── __init__.py ├── __pycache__ │ └── __init__.cpython-39.pyc └── vllm │ ├── __init__.py │ ├── __pycache__ │ └── __init__.cpython-39.pyc │ ├── vllm_v_0_3_1 │ ├── __init__.py │ ├── arg_utils.py │ ├── config.py │ ├── llm.py │ ├── llm_engine_sp.py │ ├── model_loader.py │ ├── model_runner.py │ ├── parallel_state.py │ ├── tokenizer.py │ ├── weight_loaders.py │ └── worker.py │ ├── vllm_v_0_4_2 │ ├── __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_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 │ ├── __pycache__ │ ├── __init__.cpython-39.pyc │ ├── arg_utils.cpython-39.pyc │ ├── config.cpython-39.pyc │ ├── dtensor_weight_loaders.cpython-39.pyc │ ├── hf_weight_loader.cpython-39.pyc │ ├── llm.cpython-39.pyc │ ├── llm_engine_sp.cpython-39.pyc │ ├── megatron_weight_loaders.cpython-39.pyc │ ├── model_loader.cpython-39.pyc │ ├── model_runner.cpython-39.pyc │ ├── parallel_state.cpython-39.pyc │ ├── spmd_gpu_executor.cpython-39.pyc │ ├── tokenizer.cpython-39.pyc │ └── worker.cpython-39.pyc │ ├── 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 ├── trainer ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-39.pyc │ └── main_ppo.cpython-39.pyc ├── 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 │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── core_algos.cpython-39.pyc │ │ └── ray_trainer.cpython-39.pyc │ ├── core_algos.py │ └── ray_trainer.py └── runtime_env.yaml ├── utils ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-310.pyc │ ├── __init__.cpython-39.pyc │ ├── flops_counter.cpython-39.pyc │ ├── fs.cpython-39.pyc │ ├── fsdp_utils.cpython-39.pyc │ ├── hdfs_io.cpython-310.pyc │ ├── hdfs_io.cpython-39.pyc │ ├── import_utils.cpython-39.pyc │ ├── logging_utils.cpython-310.pyc │ ├── logging_utils.cpython-39.pyc │ ├── model.cpython-39.pyc │ ├── py_functional.cpython-310.pyc │ ├── py_functional.cpython-39.pyc │ ├── seqlen_balancing.cpython-39.pyc │ ├── tokenizer.cpython-310.pyc │ ├── tokenizer.cpython-39.pyc │ ├── torch_dtypes.cpython-39.pyc │ ├── torch_functional.cpython-39.pyc │ ├── tracking.cpython-39.pyc │ └── ulysses.cpython-39.pyc ├── config.py ├── dataset │ ├── README.md │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ ├── rl_dataset.cpython-39.pyc │ │ └── rm_dataset.cpython-39.pyc │ ├── rl_dataset.py │ └── rm_dataset.py ├── debug │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ └── performance.cpython-39.pyc │ ├── performance.py │ └── trajectory_tracker.py ├── distributed.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 │ ├── optimizer_config.py │ ├── pipeline_parallel.py │ ├── sequence_parallel.py │ └── tensor_parallel.py ├── megatron_utils.py ├── memory_buffer.py ├── model.py ├── py_functional.py ├── ray_utils.py ├── rendezvous │ ├── __init__.py │ └── ray_backend.py ├── reward_score │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ └── qa_em.cpython-39.pyc │ ├── countdown.py │ ├── gsm8k.py │ ├── math.py │ ├── multiply.py │ └── qa_em.py ├── seqlen_balancing.py ├── tokenizer.py ├── torch_dtypes.py ├── torch_functional.py ├── tracking.py └── ulysses.py ├── version └── version └── workers ├── __init__.py ├── __pycache__ ├── __init__.cpython-39.pyc └── fsdp_workers.cpython-39.pyc ├── actor ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-39.pyc │ ├── base.cpython-39.pyc │ └── dp_actor.cpython-39.pyc ├── base.py ├── dp_actor.py └── megatron_actor.py ├── critic ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-39.pyc │ ├── base.cpython-39.pyc │ └── dp_critic.cpython-39.pyc ├── base.py ├── dp_critic.py └── megatron_critic.py ├── fsdp_workers.py ├── megatron_workers.py ├── retriever_workers.py ├── reward_model ├── __init__.py ├── base.py └── megatron │ ├── __init__.py │ └── reward_model.py ├── rollout ├── __init__.py ├── __pycache__ │ ├── __init__.cpython-39.pyc │ ├── base.cpython-39.pyc │ ├── hf_rollout.cpython-39.pyc │ └── tokenizer.cpython-39.pyc ├── base.py ├── hf_rollout.py ├── naive │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-39.pyc │ │ └── naive_rollout.cpython-39.pyc │ └── naive_rollout.py ├── tokenizer.py └── vllm_rollout │ ├── __init__.py │ ├── __pycache__ │ ├── __init__.cpython-39.pyc │ └── vllm_rollout.cpython-39.pyc │ └── vllm_rollout.py └── sharding_manager ├── __init__.py ├── __pycache__ ├── __init__.cpython-39.pyc ├── base.cpython-39.pyc ├── fsdp_ulysses.cpython-39.pyc └── fsdp_vllm.cpython-39.pyc ├── base.py ├── fsdp_ulysses.py ├── fsdp_vllm.py └── megatron_vllm.py /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/LICENSE -------------------------------------------------------------------------------- /Notice.txt: -------------------------------------------------------------------------------- 1 | Copyright 2023-2024 Bytedance Ltd. and/or its affiliates -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/README.md -------------------------------------------------------------------------------- /README_Search-R1.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/README_Search-R1.md -------------------------------------------------------------------------------- /VERL_README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/VERL_README.md -------------------------------------------------------------------------------- /download_corpus.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/download_corpus.sh -------------------------------------------------------------------------------- /evaluate.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/evaluate.sh -------------------------------------------------------------------------------- /evaluate_all.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/evaluate_all.sh -------------------------------------------------------------------------------- /infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/infer.py -------------------------------------------------------------------------------- /make_ikea.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/make_ikea.sh -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/pyproject.toml -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/requirements.txt -------------------------------------------------------------------------------- /retrieval_launch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/retrieval_launch.sh -------------------------------------------------------------------------------- /retrieval_log.txt: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/data_process/2wiki_knowledge_boundary.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/data_process/2wiki_knowledge_boundary.py -------------------------------------------------------------------------------- /scripts/data_process/nq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/data_process/nq.py -------------------------------------------------------------------------------- /scripts/data_process/nq_hotpotqa_knowledge_boundary.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/data_process/nq_hotpotqa_knowledge_boundary.py -------------------------------------------------------------------------------- /scripts/data_process/nq_hotpotqa_knowledge_boundary_easy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/data_process/nq_hotpotqa_knowledge_boundary_easy.py -------------------------------------------------------------------------------- /scripts/data_process/nq_hotpotqa_knowledge_boundary_hard.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/data_process/nq_hotpotqa_knowledge_boundary_hard.py -------------------------------------------------------------------------------- /scripts/data_process/nq_knowledge_boundary.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/data_process/nq_knowledge_boundary.py -------------------------------------------------------------------------------- /scripts/data_process/nq_rag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/data_process/nq_rag.py -------------------------------------------------------------------------------- /scripts/data_process/nq_search.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/data_process/nq_search.py -------------------------------------------------------------------------------- /scripts/data_process/nq_vanilla.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/data_process/nq_vanilla.py -------------------------------------------------------------------------------- /scripts/download.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/download.py -------------------------------------------------------------------------------- /scripts/download.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/download.sh -------------------------------------------------------------------------------- /scripts/e5_Flat.index: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/nq_hotpotqa/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/nq_hotpotqa/README.md -------------------------------------------------------------------------------- /scripts/nq_hotpotqa/evaluate.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/nq_hotpotqa/evaluate.sh -------------------------------------------------------------------------------- /scripts/nq_hotpotqa/train_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/nq_hotpotqa/train_grpo.sh -------------------------------------------------------------------------------- /scripts/nq_hotpotqa/train_ppo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/nq_hotpotqa/train_ppo.sh -------------------------------------------------------------------------------- /scripts/upload.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/upload.py -------------------------------------------------------------------------------- /scripts/upload.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/scripts/upload.sh -------------------------------------------------------------------------------- /search_r1/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /search_r1/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/search_r1/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /search_r1/llm_agent/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /search_r1/llm_agent/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/search_r1/llm_agent/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /search_r1/llm_agent/__pycache__/generation.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/search_r1/llm_agent/__pycache__/generation.cpython-39.pyc -------------------------------------------------------------------------------- /search_r1/llm_agent/__pycache__/tensor_helper.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/search_r1/llm_agent/__pycache__/tensor_helper.cpython-39.pyc -------------------------------------------------------------------------------- /search_r1/llm_agent/generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/search_r1/llm_agent/generation.py -------------------------------------------------------------------------------- /search_r1/llm_agent/tensor_helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/search_r1/llm_agent/tensor_helper.py -------------------------------------------------------------------------------- /search_r1/search/build_index.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/search_r1/search/build_index.sh -------------------------------------------------------------------------------- /search_r1/search/index_builder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/search_r1/search/index_builder.py -------------------------------------------------------------------------------- /search_r1/search/retrieval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/search_r1/search/retrieval.py -------------------------------------------------------------------------------- /search_r1/search/retrieval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/search_r1/search/retrieval.sh -------------------------------------------------------------------------------- /search_r1/search/retrieval_request.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/search_r1/search/retrieval_request.py -------------------------------------------------------------------------------- /search_r1/search/retrieval_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/search_r1/search/retrieval_server.py -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/setup.py -------------------------------------------------------------------------------- /sft/deepspeed_zero3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/sft/deepspeed_zero3.yaml -------------------------------------------------------------------------------- /sft/main_train_sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/sft/main_train_sft.py -------------------------------------------------------------------------------- /sft/run_train_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/sft/run_train_sft.sh -------------------------------------------------------------------------------- /train_grpo_kb.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/train_grpo_kb.sh -------------------------------------------------------------------------------- /train_grpo_vanilla.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/train_grpo_vanilla.sh -------------------------------------------------------------------------------- /verl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/__init__.py -------------------------------------------------------------------------------- /verl/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /verl/__pycache__/__init__.cpython-312.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/__pycache__/__init__.cpython-312.pyc -------------------------------------------------------------------------------- /verl/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/__pycache__/protocol.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/__pycache__/protocol.cpython-310.pyc -------------------------------------------------------------------------------- /verl/__pycache__/protocol.cpython-312.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/__pycache__/protocol.cpython-312.pyc -------------------------------------------------------------------------------- /verl/__pycache__/protocol.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/__pycache__/protocol.cpython-39.pyc -------------------------------------------------------------------------------- /verl/models/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/README.md -------------------------------------------------------------------------------- /verl/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/__init__.py -------------------------------------------------------------------------------- /verl/models/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/models/__pycache__/registry.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/__pycache__/registry.cpython-39.pyc -------------------------------------------------------------------------------- /verl/models/llama/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/llama/__init__.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/llama/megatron/__init__.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/checkpoint_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/llama/megatron/checkpoint_utils/__init__.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/checkpoint_utils/llama_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/llama/megatron/checkpoint_utils/llama_loader.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/checkpoint_utils/llama_saver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/llama/megatron/checkpoint_utils/llama_saver.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/llama/megatron/layers/__init__.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/layers/parallel_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/llama/megatron/layers/parallel_attention.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/layers/parallel_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/llama/megatron/layers/parallel_decoder.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/layers/parallel_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/llama/megatron/layers/parallel_linear.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/layers/parallel_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/llama/megatron/layers/parallel_mlp.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/layers/parallel_rmsnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/llama/megatron/layers/parallel_rmsnorm.py -------------------------------------------------------------------------------- /verl/models/llama/megatron/modeling_llama_megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/llama/megatron/modeling_llama_megatron.py -------------------------------------------------------------------------------- /verl/models/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/registry.py -------------------------------------------------------------------------------- /verl/models/transformers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/transformers/__init__.py -------------------------------------------------------------------------------- /verl/models/transformers/llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/transformers/llama.py -------------------------------------------------------------------------------- /verl/models/transformers/monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/transformers/monkey_patch.py -------------------------------------------------------------------------------- /verl/models/transformers/qwen2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/transformers/qwen2.py -------------------------------------------------------------------------------- /verl/models/weight_loader_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/models/weight_loader_registry.py -------------------------------------------------------------------------------- /verl/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/protocol.py -------------------------------------------------------------------------------- /verl/single_controller/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/__init__.py -------------------------------------------------------------------------------- /verl/single_controller/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/single_controller/base/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/__init__.py -------------------------------------------------------------------------------- /verl/single_controller/base/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/single_controller/base/__pycache__/decorator.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/__pycache__/decorator.cpython-39.pyc -------------------------------------------------------------------------------- /verl/single_controller/base/__pycache__/worker.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/__pycache__/worker.cpython-39.pyc -------------------------------------------------------------------------------- /verl/single_controller/base/__pycache__/worker_group.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/__pycache__/worker_group.cpython-39.pyc -------------------------------------------------------------------------------- /verl/single_controller/base/decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/decorator.py -------------------------------------------------------------------------------- /verl/single_controller/base/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/megatron/__init__.py -------------------------------------------------------------------------------- /verl/single_controller/base/megatron/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/megatron/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/single_controller/base/megatron/__pycache__/worker.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/megatron/__pycache__/worker.cpython-39.pyc -------------------------------------------------------------------------------- /verl/single_controller/base/megatron/__pycache__/worker_group.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/megatron/__pycache__/worker_group.cpython-39.pyc -------------------------------------------------------------------------------- /verl/single_controller/base/megatron/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/megatron/worker.py -------------------------------------------------------------------------------- /verl/single_controller/base/megatron/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/megatron/worker_group.py -------------------------------------------------------------------------------- /verl/single_controller/base/register_center/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/register_center/__init__.py -------------------------------------------------------------------------------- /verl/single_controller/base/register_center/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/register_center/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/single_controller/base/register_center/__pycache__/ray.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/register_center/__pycache__/ray.cpython-39.pyc -------------------------------------------------------------------------------- /verl/single_controller/base/register_center/ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/register_center/ray.py -------------------------------------------------------------------------------- /verl/single_controller/base/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/worker.py -------------------------------------------------------------------------------- /verl/single_controller/base/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/base/worker_group.py -------------------------------------------------------------------------------- /verl/single_controller/ray/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/ray/__init__.py -------------------------------------------------------------------------------- /verl/single_controller/ray/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/ray/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/single_controller/ray/__pycache__/base.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/ray/__pycache__/base.cpython-39.pyc -------------------------------------------------------------------------------- /verl/single_controller/ray/__pycache__/megatron.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/ray/__pycache__/megatron.cpython-39.pyc -------------------------------------------------------------------------------- /verl/single_controller/ray/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/ray/base.py -------------------------------------------------------------------------------- /verl/single_controller/ray/megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/single_controller/ray/megatron.py -------------------------------------------------------------------------------- /verl/single_controller/version/version: -------------------------------------------------------------------------------- 1 | 0.0.2 -------------------------------------------------------------------------------- /verl/third_party/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/__init__.py -------------------------------------------------------------------------------- /verl/third_party/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/__init__.py -------------------------------------------------------------------------------- /verl/third_party/vllm/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_3_1/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_3_1/__init__.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_3_1/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_3_1/arg_utils.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_3_1/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_3_1/config.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_3_1/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_3_1/llm.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_3_1/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_3_1/model_loader.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_3_1/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_3_1/model_runner.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_3_1/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_3_1/parallel_state.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_3_1/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_3_1/tokenizer.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_3_1/weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_3_1/weight_loaders.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_3_1/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_3_1/worker.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/__init__.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/arg_utils.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/config.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/dtensor_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/dtensor_weight_loaders.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/hf_weight_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/hf_weight_loader.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/llm.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/llm_engine_sp.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/model_loader.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/model_runner.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/parallel_state.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/tokenizer.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_4_2/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_4_2/worker.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/__init__.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/arg_utils.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/config.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/hf_weight_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/hf_weight_loader.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/llm.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/model_runner.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_5_4/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_5_4/worker.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__init__.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/arg_utils.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/arg_utils.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/config.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/config.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/dtensor_weight_loaders.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/dtensor_weight_loaders.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/hf_weight_loader.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/hf_weight_loader.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/llm.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/llm.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/llm_engine_sp.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/llm_engine_sp.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/megatron_weight_loaders.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/megatron_weight_loaders.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/model_loader.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/model_loader.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/model_runner.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/model_runner.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/parallel_state.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/parallel_state.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/spmd_gpu_executor.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/spmd_gpu_executor.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/tokenizer.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/tokenizer.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/__pycache__/worker.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/__pycache__/worker.cpython-39.pyc -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/config.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/hf_weight_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/hf_weight_loader.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/llm.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/model_runner.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/tokenizer.py -------------------------------------------------------------------------------- /verl/third_party/vllm/vllm_v_0_6_3/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/third_party/vllm/vllm_v_0_6_3/worker.py -------------------------------------------------------------------------------- /verl/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/__init__.py -------------------------------------------------------------------------------- /verl/trainer/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/trainer/__pycache__/main_ppo.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/__pycache__/main_ppo.cpython-39.pyc -------------------------------------------------------------------------------- /verl/trainer/config/evaluation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/config/evaluation.yaml -------------------------------------------------------------------------------- /verl/trainer/config/generation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/config/generation.yaml -------------------------------------------------------------------------------- /verl/trainer/config/ppo_megatron_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/config/ppo_megatron_trainer.yaml -------------------------------------------------------------------------------- /verl/trainer/config/ppo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/config/ppo_trainer.yaml -------------------------------------------------------------------------------- /verl/trainer/config/sft_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/config/sft_trainer.yaml -------------------------------------------------------------------------------- /verl/trainer/fsdp_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/fsdp_sft_trainer.py -------------------------------------------------------------------------------- /verl/trainer/main_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/main_eval.py -------------------------------------------------------------------------------- /verl/trainer/main_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/main_generation.py -------------------------------------------------------------------------------- /verl/trainer/main_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/main_ppo.py -------------------------------------------------------------------------------- /verl/trainer/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/ppo/__init__.py -------------------------------------------------------------------------------- /verl/trainer/ppo/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/ppo/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/trainer/ppo/__pycache__/core_algos.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/ppo/__pycache__/core_algos.cpython-39.pyc -------------------------------------------------------------------------------- /verl/trainer/ppo/__pycache__/ray_trainer.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/ppo/__pycache__/ray_trainer.cpython-39.pyc -------------------------------------------------------------------------------- /verl/trainer/ppo/core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/ppo/core_algos.py -------------------------------------------------------------------------------- /verl/trainer/ppo/ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/ppo/ray_trainer.py -------------------------------------------------------------------------------- /verl/trainer/runtime_env.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/trainer/runtime_env.yaml -------------------------------------------------------------------------------- /verl/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__init__.py -------------------------------------------------------------------------------- /verl/utils/__pycache__/__init__.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/__init__.cpython-310.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/flops_counter.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/flops_counter.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/fs.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/fs.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/fsdp_utils.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/fsdp_utils.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/hdfs_io.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/hdfs_io.cpython-310.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/hdfs_io.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/hdfs_io.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/import_utils.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/import_utils.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/logging_utils.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/logging_utils.cpython-310.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/logging_utils.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/logging_utils.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/model.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/model.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/py_functional.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/py_functional.cpython-310.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/py_functional.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/py_functional.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/seqlen_balancing.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/seqlen_balancing.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/tokenizer.cpython-310.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/tokenizer.cpython-310.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/tokenizer.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/tokenizer.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/torch_dtypes.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/torch_dtypes.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/torch_functional.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/torch_functional.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/tracking.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/tracking.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/__pycache__/ulysses.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/__pycache__/ulysses.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/config.py -------------------------------------------------------------------------------- /verl/utils/dataset/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/dataset/README.md -------------------------------------------------------------------------------- /verl/utils/dataset/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/dataset/__init__.py -------------------------------------------------------------------------------- /verl/utils/dataset/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/dataset/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/dataset/__pycache__/rl_dataset.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/dataset/__pycache__/rl_dataset.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/dataset/__pycache__/rm_dataset.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/dataset/__pycache__/rm_dataset.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/dataset/rl_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/dataset/rl_dataset.py -------------------------------------------------------------------------------- /verl/utils/dataset/rm_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/dataset/rm_dataset.py -------------------------------------------------------------------------------- /verl/utils/debug/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/debug/__init__.py -------------------------------------------------------------------------------- /verl/utils/debug/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/debug/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/debug/__pycache__/performance.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/debug/__pycache__/performance.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/debug/performance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/debug/performance.py -------------------------------------------------------------------------------- /verl/utils/debug/trajectory_tracker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/debug/trajectory_tracker.py -------------------------------------------------------------------------------- /verl/utils/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/distributed.py -------------------------------------------------------------------------------- /verl/utils/flops_counter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/flops_counter.py -------------------------------------------------------------------------------- /verl/utils/fs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/fs.py -------------------------------------------------------------------------------- /verl/utils/fsdp_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/fsdp_utils.py -------------------------------------------------------------------------------- /verl/utils/hdfs_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/hdfs_io.py -------------------------------------------------------------------------------- /verl/utils/import_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/import_utils.py -------------------------------------------------------------------------------- /verl/utils/logger/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/logger/__init__.py -------------------------------------------------------------------------------- /verl/utils/logger/aggregate_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/logger/aggregate_logger.py -------------------------------------------------------------------------------- /verl/utils/logging_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/logging_utils.py -------------------------------------------------------------------------------- /verl/utils/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/megatron/__init__.py -------------------------------------------------------------------------------- /verl/utils/megatron/memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/megatron/memory.py -------------------------------------------------------------------------------- /verl/utils/megatron/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/megatron/optimizer.py -------------------------------------------------------------------------------- /verl/utils/megatron/optimizer_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/megatron/optimizer_config.py -------------------------------------------------------------------------------- /verl/utils/megatron/pipeline_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/megatron/pipeline_parallel.py -------------------------------------------------------------------------------- /verl/utils/megatron/sequence_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/megatron/sequence_parallel.py -------------------------------------------------------------------------------- /verl/utils/megatron/tensor_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/megatron/tensor_parallel.py -------------------------------------------------------------------------------- /verl/utils/megatron_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/megatron_utils.py -------------------------------------------------------------------------------- /verl/utils/memory_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/memory_buffer.py -------------------------------------------------------------------------------- /verl/utils/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/model.py -------------------------------------------------------------------------------- /verl/utils/py_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/py_functional.py -------------------------------------------------------------------------------- /verl/utils/ray_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/ray_utils.py -------------------------------------------------------------------------------- /verl/utils/rendezvous/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/rendezvous/__init__.py -------------------------------------------------------------------------------- /verl/utils/rendezvous/ray_backend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/rendezvous/ray_backend.py -------------------------------------------------------------------------------- /verl/utils/reward_score/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/reward_score/__init__.py -------------------------------------------------------------------------------- /verl/utils/reward_score/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/reward_score/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/reward_score/__pycache__/qa_em.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/reward_score/__pycache__/qa_em.cpython-39.pyc -------------------------------------------------------------------------------- /verl/utils/reward_score/countdown.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/reward_score/countdown.py -------------------------------------------------------------------------------- /verl/utils/reward_score/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/reward_score/gsm8k.py -------------------------------------------------------------------------------- /verl/utils/reward_score/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/reward_score/math.py -------------------------------------------------------------------------------- /verl/utils/reward_score/multiply.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/reward_score/multiply.py -------------------------------------------------------------------------------- /verl/utils/reward_score/qa_em.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/reward_score/qa_em.py -------------------------------------------------------------------------------- /verl/utils/seqlen_balancing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/seqlen_balancing.py -------------------------------------------------------------------------------- /verl/utils/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/tokenizer.py -------------------------------------------------------------------------------- /verl/utils/torch_dtypes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/torch_dtypes.py -------------------------------------------------------------------------------- /verl/utils/torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/torch_functional.py -------------------------------------------------------------------------------- /verl/utils/tracking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/tracking.py -------------------------------------------------------------------------------- /verl/utils/ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/utils/ulysses.py -------------------------------------------------------------------------------- /verl/version/version: -------------------------------------------------------------------------------- 1 | 0.1 -------------------------------------------------------------------------------- /verl/workers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/__init__.py -------------------------------------------------------------------------------- /verl/workers/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/__pycache__/fsdp_workers.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/__pycache__/fsdp_workers.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/actor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/actor/__init__.py -------------------------------------------------------------------------------- /verl/workers/actor/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/actor/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/actor/__pycache__/base.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/actor/__pycache__/base.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/actor/__pycache__/dp_actor.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/actor/__pycache__/dp_actor.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/actor/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/actor/base.py -------------------------------------------------------------------------------- /verl/workers/actor/dp_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/actor/dp_actor.py -------------------------------------------------------------------------------- /verl/workers/actor/megatron_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/actor/megatron_actor.py -------------------------------------------------------------------------------- /verl/workers/critic/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/critic/__init__.py -------------------------------------------------------------------------------- /verl/workers/critic/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/critic/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/critic/__pycache__/base.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/critic/__pycache__/base.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/critic/__pycache__/dp_critic.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/critic/__pycache__/dp_critic.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/critic/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/critic/base.py -------------------------------------------------------------------------------- /verl/workers/critic/dp_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/critic/dp_critic.py -------------------------------------------------------------------------------- /verl/workers/critic/megatron_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/critic/megatron_critic.py -------------------------------------------------------------------------------- /verl/workers/fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/fsdp_workers.py -------------------------------------------------------------------------------- /verl/workers/megatron_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/megatron_workers.py -------------------------------------------------------------------------------- /verl/workers/retriever_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/retriever_workers.py -------------------------------------------------------------------------------- /verl/workers/reward_model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/reward_model/__init__.py -------------------------------------------------------------------------------- /verl/workers/reward_model/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/reward_model/base.py -------------------------------------------------------------------------------- /verl/workers/reward_model/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/reward_model/megatron/__init__.py -------------------------------------------------------------------------------- /verl/workers/reward_model/megatron/reward_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/reward_model/megatron/reward_model.py -------------------------------------------------------------------------------- /verl/workers/rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/__init__.py -------------------------------------------------------------------------------- /verl/workers/rollout/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/rollout/__pycache__/base.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/__pycache__/base.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/rollout/__pycache__/hf_rollout.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/__pycache__/hf_rollout.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/rollout/__pycache__/tokenizer.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/__pycache__/tokenizer.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/rollout/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/base.py -------------------------------------------------------------------------------- /verl/workers/rollout/hf_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/hf_rollout.py -------------------------------------------------------------------------------- /verl/workers/rollout/naive/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/naive/__init__.py -------------------------------------------------------------------------------- /verl/workers/rollout/naive/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/naive/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/rollout/naive/__pycache__/naive_rollout.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/naive/__pycache__/naive_rollout.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/rollout/naive/naive_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/naive/naive_rollout.py -------------------------------------------------------------------------------- /verl/workers/rollout/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/tokenizer.py -------------------------------------------------------------------------------- /verl/workers/rollout/vllm_rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/vllm_rollout/__init__.py -------------------------------------------------------------------------------- /verl/workers/rollout/vllm_rollout/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/vllm_rollout/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/rollout/vllm_rollout/__pycache__/vllm_rollout.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/vllm_rollout/__pycache__/vllm_rollout.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/rollout/vllm_rollout/vllm_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/rollout/vllm_rollout/vllm_rollout.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/sharding_manager/__init__.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/__pycache__/__init__.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/sharding_manager/__pycache__/__init__.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/sharding_manager/__pycache__/base.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/sharding_manager/__pycache__/base.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/sharding_manager/__pycache__/fsdp_ulysses.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/sharding_manager/__pycache__/fsdp_ulysses.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/sharding_manager/__pycache__/fsdp_vllm.cpython-39.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/sharding_manager/__pycache__/fsdp_vllm.cpython-39.pyc -------------------------------------------------------------------------------- /verl/workers/sharding_manager/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/sharding_manager/base.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/fsdp_ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/sharding_manager/fsdp_ulysses.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/sharding_manager/fsdp_vllm.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/megatron_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/hzy312/knowledge-r1/HEAD/verl/workers/sharding_manager/megatron_vllm.py --------------------------------------------------------------------------------