├── .dockerignore ├── .github ├── actions │ ├── push │ │ └── action.yaml │ └── setup │ │ └── action.yaml └── workflows │ ├── beaker-experiment.yml │ ├── docs.yml │ ├── push-image.yml │ ├── quality.yml │ └── tests.yml ├── .gitignore ├── AGENTS.md ├── CLAUDE.md ├── Dockerfile ├── LICENSE ├── Makefile ├── README.md ├── assets ├── images │ └── tulu_logo.png └── model_licenses │ ├── llama_license.txt │ ├── opt_license.txt │ ├── pythia_license.txt │ └── tulu_license.txt ├── configs ├── beaker_configs │ ├── alpaca_7B.yaml │ ├── alpaca_7B_lora.yaml │ ├── code_api_setup.sh │ ├── default_dpo.yaml │ ├── default_dpo_multinode.yaml │ ├── default_dpo_multinode_olmo2_1124.yaml │ ├── default_dpo_multinode_olmo2_1124_augusta.yaml │ ├── default_eval.yaml │ ├── default_finetune.yaml │ ├── default_finetune_lora_multinode.yaml │ ├── default_finetune_multinode.yaml │ ├── default_finetune_multinode_olmo2_1124.yaml │ ├── default_finetune_multinode_olmo2_1124_augusta.yaml │ ├── default_finetune_qlora_multinode.yaml │ ├── ray_node_setup.sh │ └── run_weight_diff.sh ├── ds_configs │ ├── deepspeed_zero2.yaml │ ├── deepspeed_zero3.yaml │ ├── stage2_accelerate.conf │ ├── stage3_no_offloading.conf │ ├── stage3_no_offloading_accelerate.conf │ ├── stage3_offloading.conf │ └── stage3_offloading_accelerate.conf ├── judge_configs │ └── general_verifier_judge.yaml └── train_configs │ ├── dpo │ ├── default.yaml │ ├── final_best_70b_dpo_config.yaml │ ├── final_best_8b_dpo_config.yaml │ ├── mini.yaml │ ├── olmo_1b_mix_example.yaml │ ├── olmo_7b_17_inst.yaml │ ├── tulu3_preview_pref_v3.0.yaml │ ├── tulu3_preview_pref_v3.1.yaml │ ├── tulu3_preview_pref_v3.2.yaml │ ├── tulu3_preview_pref_v3.3.yaml │ ├── tulu3_preview_test_simpo.yaml │ ├── tulu_3_preview_test_if_faeze.yaml │ ├── valpy_dpo.yaml │ └── valpy_dpo_mix_new.yaml │ ├── olmo2 │ ├── olmo2_1124_13b_dpo.yaml │ ├── olmo2_1124_13b_sft.yaml │ ├── olmo2_1124_32b_dpo.yaml │ ├── olmo2_1124_7b_dpo.yaml │ └── olmo2_1124_7b_sft.yaml │ ├── sft │ ├── default.yaml │ ├── mini.yaml │ ├── olmo_7b_17_remix_sft.yaml │ ├── olmo_7b_17_safe_sft.yaml │ ├── olmo_7b_17_sft.yaml │ ├── olmo_7b_sft.yaml │ ├── olmoe_preview_mix_v3.1.yaml │ ├── tulu2_13b.yaml │ ├── tulu2_70b.yaml │ ├── tulu2_7b.yaml │ ├── tulu2_7b_lora.yaml │ ├── tulu2_7b_qlora.yaml │ ├── tulu2_7b_remix.yaml │ ├── tulu3_70b_preview_mix_v3.8-commercial.yaml │ ├── tulu3_70b_preview_mix_v3.8-noncommercial.yaml │ ├── tulu3_70b_preview_mix_v3.9-noncommercial.yaml │ ├── tulu3_8b_no_robot.yaml │ ├── tulu3_8b_preview_mix_v3.0.yaml │ ├── tulu3_8b_preview_mix_v3.1.yaml │ ├── tulu3_8b_preview_mix_v3.10.yaml │ ├── tulu3_8b_preview_mix_v3.2.yaml │ ├── tulu3_8b_preview_mix_v3.3.yaml │ ├── tulu3_8b_preview_mix_v3.4.x │ │ ├── tulu3_8b_preview_mix_v3.4.0.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.1.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.10.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.11.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.12.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.13.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.14.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.15.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.16.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.17.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.18.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.19.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.2.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.20.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.21.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.22.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.23.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.24.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.25.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.26.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.27.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.28.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.29.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.3.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.30.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.31.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.32.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.4.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.5.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.6.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.7.yaml │ │ ├── tulu3_8b_preview_mix_v3.4.8.yaml │ │ └── tulu3_8b_preview_mix_v3.4.9.yaml │ ├── tulu3_8b_preview_mix_v3.4.yaml │ ├── tulu3_8b_preview_mix_v3.5.x │ │ ├── llama3.1_8b_preview_mix_v3.5.1.yaml │ │ ├── llama3.1_8b_preview_mix_v3.5.10.yaml │ │ ├── llama3.1_8b_preview_mix_v3.5.11.yaml │ │ ├── llama3.1_8b_preview_mix_v3.5.12.yaml │ │ ├── llama3.1_8b_preview_mix_v3.5.13.yaml │ │ ├── llama3.1_8b_preview_mix_v3.5.2.yaml │ │ ├── llama3.1_8b_preview_mix_v3.5.3.yaml │ │ ├── llama3.1_8b_preview_mix_v3.5.4.yaml │ │ ├── llama3.1_8b_preview_mix_v3.5.5.yaml │ │ ├── llama3.1_8b_preview_mix_v3.5.6.yaml │ │ ├── llama3.1_8b_preview_mix_v3.5.7.yaml │ │ ├── llama3.1_8b_preview_mix_v3.5.8.yaml │ │ └── llama3.1_8b_preview_mix_v3.5.9.yaml │ ├── tulu3_8b_preview_mix_v3.6.yaml │ ├── tulu3_8b_preview_mix_v3.7.yaml │ ├── tulu3_8b_preview_mix_v3.8-commercial.yaml │ ├── tulu3_8b_preview_mix_v3.8-noncommercial.yaml │ ├── tulu3_8b_preview_mix_v3.9-noncommercial.yaml │ ├── tulu3_L3.1_70b_preview_mix_v3.3.yaml │ └── tulu3_L3.1_8b_math_faeze.yaml │ └── tulu3 │ ├── tulu3_dpo_70b.yaml │ ├── tulu3_dpo_8b.yaml │ └── tulu3_sft.yaml ├── decontamination ├── README.md ├── index.py └── search.py ├── docs ├── ai2_internal.md ├── algorithms │ ├── dataset │ │ ├── sft.png │ │ └── sft2.png │ ├── dataset_transformation.md │ ├── dpo.md │ ├── dpo │ │ ├── olmo2_13b_dpo-time.png │ │ ├── olmo2_13b_dpo.png │ │ ├── olmo2_13b_dpo_eval.png │ │ ├── olmo2_7b_dpo-time.png │ │ ├── olmo2_7b_dpo.png │ │ ├── olmo2_7b_dpo_eval.png │ │ ├── tulu3_8b_dpo-time.png │ │ ├── tulu3_8b_dpo.png │ │ ├── tulu3_8b_dpo_eval.png │ │ └── tulu3_8b_dpo_eval_drop.png │ ├── finetune.md │ ├── finetune │ │ ├── finetune_debug.png │ │ ├── olmo2_13b_sft-time.png │ │ ├── olmo2_13b_sft.png │ │ ├── olmo2_32b_sft-time.png │ │ ├── olmo2_32b_sft.png │ │ ├── olmo2_32b_sft_eval.png │ │ ├── olmo2_7b_sft-time.png │ │ ├── olmo2_7b_sft.png │ │ ├── olmo2_7b_sft_eval.png │ │ ├── tulu3_8b.png │ │ ├── tulu3_8b_eval.png │ │ ├── tulu3_8b_sft-time.png │ │ └── tulu3_8b_sft.png │ ├── grpo.md │ ├── grpo │ │ ├── additive_format_reward.png │ │ ├── grpo_fast_gradient.png │ │ ├── olmo2_13b_grpo_fast_zero-time.png │ │ ├── olmo2_13b_grpo_fast_zero.png │ │ ├── olmo2_13b_grpo_fast_zero_eval_curve.png │ │ ├── olmo2_7b_grpo-time.png │ │ ├── olmo2_7b_grpo.png │ │ ├── olmo2_7b_grpo_eval.png │ │ ├── olmo2_7b_grpo_eval_curve.png │ │ ├── olmo2_7b_grpo_fast_zero-time.png │ │ ├── olmo2_7b_grpo_fast_zero.png │ │ ├── olmo2_7b_grpo_fast_zero_eval_curve.png │ │ ├── qwen2.5_7b_grpo_fast_zero-time.png │ │ ├── qwen2.5_7b_grpo_fast_zero.png │ │ ├── qwen2.5_7b_grpo_fast_zero_eval_curve.png │ │ ├── qwen2.5_7b_grpo_zero-time.png │ │ ├── qwen2.5_7b_grpo_zero.png │ │ ├── qwen2.5_7b_grpo_zero_eval_curve.png │ │ ├── tulu3.1_8b_grpo-time.png │ │ ├── tulu3.1_8b_grpo.png │ │ ├── tulu3.1_8b_grpo_eval.png │ │ ├── tulu3.1_8b_grpo_eval_curve.png │ │ ├── tulu3.1_8b_grpo_fast-time.png │ │ ├── tulu3.1_8b_grpo_fast.png │ │ ├── tulu3.1_8b_grpo_fast_eval.png │ │ └── tulu3.1_8b_grpo_fast_eval_curve.png │ ├── grpo_8b.png │ ├── online_dpo.md │ ├── plot │ │ └── finetune_plot.sh │ ├── ppo.md │ ├── rejection_sampling.md │ ├── reward_modeling.md │ ├── reward_modeling │ │ ├── tulu3_8b_rm-time.png │ │ └── tulu3_8b_rm.png │ ├── reward_modeling_colored_tokens.png │ ├── reward_modeling_ds.png │ ├── reward_modeling_hf_repo.png │ ├── reward_modeling_hf_viz.png │ ├── reward_modeling_preference_sample_texts.png │ ├── reward_modeling_token.png │ ├── reward_modeling_token_wandb.png │ ├── static │ │ ├── grpo_qwen2.5_7B_works.png │ │ ├── grpo_qwen2.5_7B_works_evals.png │ │ └── grpo_qwen_fast_2.5_7B.png │ ├── synthetic_preference_dataset.md │ ├── synthetic_preference_dataset.png │ ├── trained_model_location.md │ └── trained_model_location │ │ ├── beaker_dataset.gif │ │ ├── gsc.png │ │ ├── hf.png │ │ ├── hf2.png │ │ └── local.png ├── archived_dev_scripts │ ├── olmo2_1124.sh │ └── olmoe_0125.sh ├── assets │ ├── favicon.ico │ └── images │ │ └── tulu_logo.png ├── data │ └── preference-data.md ├── get_started │ ├── ai2_internal_setup.md │ ├── installation.md │ ├── internal_leaderboard.png │ ├── mason.png │ ├── mason_job.png │ └── vscode.png ├── index.md ├── olmo2.md ├── safety-eval │ └── safety.md ├── safety.md ├── stylesheets │ └── extra.css ├── tulu1_tulu2.md └── tulu3.md ├── human_eval ├── README.md ├── app.py ├── compute_metrics.py ├── data │ ├── eval_annotations_tulu_1.xlsx │ └── eval_instances_tulu_1.jsonl ├── export_db.py ├── requirements.txt ├── screenshot.png ├── static │ ├── app.js │ ├── favicon.png │ └── styles.css └── templates │ ├── index.html │ └── login.html ├── mason.py ├── mkdocs.yml ├── open_instruct ├── IFEvalG │ ├── instructions.py │ ├── instructions_registry.py │ └── instructions_util.py ├── __init__.py ├── actor_manager.py ├── benchmark_generators.py ├── code_utils │ ├── Dockerfile │ ├── __init__.py │ ├── api.py │ ├── code_utils.py │ ├── test_api.py │ ├── test_code_utils.py │ └── testing_util.py ├── context_window_checker.py ├── data_loader.py ├── data_types.py ├── dataset_processor.py ├── dataset_transformation.py ├── dpo_tune_cache.py ├── dpo_utils.py ├── experimental │ ├── oai_generate.py │ └── test.jsonl ├── finetune.py ├── ground_truth_utils.py ├── grpo_fast.py ├── if_functions.py ├── judge_utils.py ├── logger_utils.py ├── math_utils.py ├── merge_lora.py ├── mix_data.py ├── mix_data_preferences.py ├── model_utils.py ├── olmo_adapter │ └── __init__.py ├── padding_free_collator.py ├── ppo.py ├── rejection_sampling │ ├── __init__.py │ ├── api_generate.py │ ├── generation.py │ ├── prompt_templates.py │ ├── rejection_sampling.py │ └── synthetic_preference_dataset.py ├── reward_modeling.py ├── reward_modeling_eval.py ├── rl_utils.py ├── search_utils │ ├── massive_ds.py │ ├── s2.py │ ├── search_tool.py │ └── you.py ├── static │ ├── dashboard.css │ └── dashboard.html ├── test_benchmark_generators.py ├── test_data │ └── mbu_reproduction_cases.json ├── test_data_loader.py ├── test_dataset_processor.py ├── test_dataset_transformation.py ├── test_ground_truth_utils.py ├── test_grpo_fast.py ├── test_math_utils.py ├── test_model_utils.py ├── test_padding_free_collator.py ├── test_rl_utils.py ├── test_utils.py ├── test_vllm_utils.py ├── tool_utils │ ├── Dockerfile │ ├── requirements.txt │ ├── test_tools.py │ ├── tool_server.py │ └── tools.py ├── tools │ └── system_prompts │ │ └── debug_system_prompt.txt ├── utils.py ├── vllm_utils.py └── vllm_utils_workerwrap.py ├── pyproject.toml ├── requirements.txt ├── scripts ├── README.md ├── add_metadata.py ├── add_metadata_from_wandb.py ├── benchmarking │ ├── launch_benchmark_single_gpu.sh │ ├── launch_benchmark_single_node.sh │ └── olmo3_infra.sh ├── cache_hf.py ├── collect_eval_results.py ├── convert_olmo_1124_weights_to_hf.py ├── create_ground_truth_data.py ├── data │ ├── azure_batch │ │ ├── README.md │ │ ├── check_azure_batch_status.py │ │ ├── process_azure_batch_results.py │ │ └── regenerate_dataset_completions.py │ ├── build_hardcoded.py │ ├── convert_general_thought_to_tulu_thinker.py │ ├── convert_sft_data_for_olmocore.py │ ├── create_deepscaler_data.py │ ├── create_gpqa_data.py │ ├── create_long_form_qa_data.py │ ├── create_nq_tqa_hotpotqa_2wiki_simplqa_data.py │ ├── create_thinker_tulu_data.py │ ├── filtering_and_updates │ │ ├── README.md │ │ ├── TEST_README.md │ │ ├── filter_chinese.py │ │ ├── filter_chinese_batch.sh │ │ ├── filter_cots.py │ │ ├── filter_cutoff_date.py │ │ ├── filter_dataset_by_keywords.py │ │ ├── filter_datasets_sequential.sh │ │ ├── filter_ngram_repetitions.py │ │ ├── filter_repetition.sh │ │ ├── filter_special_tokens.py │ │ ├── filter_wildchat.py │ │ ├── run_tests.py │ │ ├── test_filter_ngram_repetitions.py │ │ └── update_subsets.py │ ├── finetune_dataset_transformation.py │ ├── get_statistics.py │ ├── get_statistics_tulu_v3.sh │ ├── get_token_distribution.py │ ├── gsm8k.py │ ├── make_eurus2_data.py │ ├── preferences │ │ ├── __init__.py │ │ ├── dataset_info.py │ │ ├── helpsteer2.py │ │ ├── helpsteer2_nvidia.py │ │ ├── hh-harmless.py │ │ ├── hh-helpful.py │ │ ├── nectar.py │ │ ├── prepare_all.sh │ │ ├── split_tulu2.5_prefs.py │ │ ├── ultrafeedback_replications.py │ │ ├── ultrainteract.py │ │ ├── utils.py │ │ └── webgpt.py │ ├── read_statistics.py │ ├── rlvr │ │ ├── acecoder.py │ │ ├── filter_existing_dataset_correctness.py │ │ ├── filtering_vllm.py │ │ ├── gsm8k_rlvr.py │ │ └── open_reasoner.py │ ├── rlvr_code │ │ ├── code_create_batch.py │ │ ├── code_create_batch_solution.py │ │ ├── code_create_batch_stdio.py │ │ ├── code_create_batch_translate.py │ │ ├── code_upload_batch.py │ │ ├── code_upload_batch_difficulty.py │ │ ├── code_upload_batch_stdio.py │ │ ├── code_upload_batch_translate.py │ │ ├── filter_seq_len.py │ │ ├── grade_difficulty.py │ │ ├── plot_seq_len.py │ │ ├── rlvr_to_sft.py │ │ ├── sft_to_rlvr_azure.py │ │ ├── the_algorithms.py │ │ └── verify_qwq.py │ ├── scripts │ │ └── data │ │ │ └── create_asqa_data.py │ ├── sft │ │ ├── aya.py │ │ ├── coconot.py │ │ ├── codefeedback_mix.py │ │ ├── daring_anteater.py │ │ ├── evol_codealpaca.py │ │ ├── flan.py │ │ ├── lima.py │ │ ├── llama_nemotron.py │ │ ├── lmsys_chat.py │ │ ├── metamath.py │ │ ├── no_robots.py │ │ ├── numinamath.py │ │ ├── open_assistant.py │ │ ├── open_code_reasoner.py │ │ ├── open_math_instruct.py │ │ ├── prepare_all.sh │ │ ├── sciriff.py │ │ ├── sharegpt.py │ │ ├── slim_orca.py │ │ ├── table_gpt.py │ │ ├── tulu_hard_coded.py │ │ ├── utils.py │ │ ├── web_instruct.py │ │ ├── wildchat.py │ │ └── wizardlm.py │ └── sft_v1_v2 │ │ ├── get_statistics.sh │ │ ├── prepare_science_data.py │ │ ├── prepare_tulu_v1_v2.sh │ │ ├── reformat_datasets.py │ │ ├── resample_flan_v2.py │ │ └── split_sharegpt_conversations.py ├── does_prompt_make_sense.py ├── dpo_train_with_accelerate.sh ├── dpo_train_with_accelerate_config.sh ├── dpo_train_with_qlora.sh ├── eval │ ├── MATH.sh │ ├── alpaca_farm.sh │ ├── bbh.sh │ ├── bfcl_supported_models.sh │ ├── codex_humaneval.sh │ ├── dummy_length_scorer.py │ ├── faster_oe_eval_mmlu.sh │ ├── fetch_mmlu_jobs.py │ ├── gsm.sh │ ├── ifeval.sh │ ├── mbpp.sh │ ├── mmlu.sh │ ├── oe-eval.sh │ ├── toxigen.sh │ ├── truthfulqa.sh │ ├── tulu3_baselines.sh │ ├── tulu3_baselines_unseen.sh │ ├── tydiqa.sh │ └── xstest.sh ├── eval_constraints │ └── if_functions.py ├── export_chat_template.py ├── finetune_lora_with_accelerate.sh ├── finetune_lora_with_accelerate_config.sh ├── finetune_qlora_with_accelerate.sh ├── finetune_qlora_with_accelerate_config.sh ├── finetune_with_accelerate.sh ├── finetune_with_accelerate_config.sh ├── persona_driven_data_gen │ ├── README.md │ ├── data │ │ └── if_constraint_fewshots_handwritten.json │ ├── persona_driven_generate_ifdata.py │ ├── persona_driven_generate_math_code.py │ ├── prompt_templates.py │ └── requirements.txt ├── rejection_sampling_tulu.bash ├── rejection_sampling_tulu_docker.bash ├── submit_dpo_job.py ├── submit_eval_jobs.py ├── submit_finetune_job.py ├── submit_finetune_jobs.sh ├── synth_pref │ ├── README.md │ ├── __init__.py │ ├── annotate_preferences.py │ ├── assets │ │ ├── ufpp_pipeline_v2_code.png │ │ └── ufpp_pipeline_v2_normal.png │ ├── create_annotation_mix.py │ ├── example │ │ ├── create_annotation_mix_out │ │ │ ├── full │ │ │ │ ├── helpfulness-full.jsonl │ │ │ │ ├── honesty-full.jsonl │ │ │ │ ├── instruction_following-full.jsonl │ │ │ │ └── truthfulness-full.jsonl │ │ │ └── myprompts │ │ │ │ ├── helpfulness │ │ │ │ └── helpfulness___shard-000000.jsonl │ │ │ │ ├── honesty │ │ │ │ └── honesty___shard-000000.jsonl │ │ │ │ ├── instruction_following │ │ │ │ └── instruction_following___shard-000000.jsonl │ │ │ │ └── truthfulness │ │ │ │ └── truthfulness___shard-000000.jsonl │ │ ├── generate_responses_in │ │ │ └── input_file.jsonl │ │ └── generate_responses_out │ │ │ ├── model0 │ │ │ └── input_file.jsonl │ │ │ ├── model1 │ │ │ └── input_file.jsonl │ │ │ ├── model2 │ │ │ └── input_file.jsonl │ │ │ └── model3 │ │ │ └── input_file.jsonl │ ├── generate_responses.py │ ├── parse_preferences.py │ ├── requirements.txt │ └── utils │ │ ├── __init__.py │ │ ├── model_configs.py │ │ ├── openai_api.py │ │ └── ultrafeedback_template.py ├── synthetic_preference_dataset.bash ├── test_chat_templates.py ├── train │ ├── benchmark.sh │ ├── build_image_and_launch.sh │ ├── build_image_and_launch_dirty.sh │ ├── debug │ │ ├── code.sh │ │ ├── cute_debug_system_prompt.txt │ │ ├── dpo.sh │ │ ├── finetune.sh │ │ ├── full_integration_test.sh │ │ ├── grpo.sh │ │ ├── grpo_fast.sh │ │ ├── grpo_fast_3_gpu.sh │ │ ├── grpo_fast_llm_judge.sh │ │ ├── grpo_fast_tool.sh │ │ ├── judge.sh │ │ ├── large_test_script.sh │ │ ├── local_tool_grpo_fast.sh │ │ ├── ppo.sh │ │ ├── ppo_fast.sh │ │ ├── ppo_fast_2_gpu.sh │ │ ├── reward_modeling.sh │ │ ├── single_gpu_integration_test.sh │ │ ├── single_gpu_on_beaker.sh │ │ └── tool_grpo_fast.sh │ ├── olmo2 │ │ ├── dpo_13b.sh │ │ ├── dpo_7b.sh │ │ ├── finetune_13b.sh │ │ ├── finetune_32b.sh │ │ ├── finetune_7b.sh │ │ ├── grpo_13b.sh │ │ ├── grpo_7b.sh │ │ ├── grpo_fast_13b_zero.sh │ │ ├── grpo_fast_32b.sh │ │ ├── grpo_fast_32b_tulu.sh │ │ └── grpo_fast_7b_zero.sh │ ├── olmo3 │ │ ├── 32b_think_dpo.sh │ │ ├── 32b_think_rl.sh │ │ ├── 7b_instruct_dpo.sh │ │ ├── 7b_instruct_rl.sh │ │ ├── 7b_rlzero_code.sh │ │ ├── 7b_rlzero_general.sh │ │ ├── 7b_rlzero_instruction_following.sh │ │ ├── 7b_rlzero_math.sh │ │ ├── 7b_rlzero_mix.sh │ │ ├── 7b_think_dpo.sh │ │ ├── 7b_think_rl.sh │ │ ├── 7b_think_rl_no_pipeline.sh │ │ └── README.md │ ├── qwen │ │ ├── finetune_7b.sh │ │ ├── grpo_7b.sh │ │ ├── grpo_fast_32b.sh │ │ ├── grpo_fast_3b_single_node.sh │ │ ├── grpo_fast_7b.sh │ │ ├── grpo_fast_7b_code.sh │ │ ├── grpo_fast_7b_orz.sh │ │ └── ppo_fast_7b_orz.sh │ ├── rlvr │ │ ├── grpo_fast_mini copy.sh │ │ ├── grpo_fast_mini_old.sh │ │ ├── grpo_llama3.1-8b.sh │ │ ├── grpo_mini_base.sh │ │ ├── grpo_mini_base_fast.sh │ │ ├── grpo_mini_base_fast1.sh │ │ ├── grpo_mini_base_fast1_test_oom.sh │ │ ├── grpo_qwen_fast_2.5_7B_best.sh │ │ ├── judge_general_verifier.sh │ │ ├── tulu_rlvr.sh │ │ ├── valpy_if.sh │ │ └── valpy_if_grpo_fast.sh │ └── tulu3 │ │ ├── dpo_8b.sh │ │ ├── finetune_8b.sh │ │ ├── grpo_8b.sh │ │ ├── grpo_fast_8b.sh │ │ ├── grpo_fast_8b_code_dpo.sh │ │ ├── grpo_fast_8b_code_sft.sh │ │ ├── grpo_fast_8b_single_node.sh │ │ ├── ppo_8b.sh │ │ └── reward_modeling_8b.sh ├── wait_beaker_dataset_model_upload_then_evaluate_model.py └── weights │ ├── convert_llama_weights_to_hf.sh │ └── weight_diff.py ├── test_mason.py └── uv.lock /.dockerignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/.dockerignore -------------------------------------------------------------------------------- /.github/actions/push/action.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/.github/actions/push/action.yaml -------------------------------------------------------------------------------- /.github/actions/setup/action.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/.github/actions/setup/action.yaml -------------------------------------------------------------------------------- /.github/workflows/beaker-experiment.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/.github/workflows/beaker-experiment.yml -------------------------------------------------------------------------------- /.github/workflows/docs.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/.github/workflows/docs.yml -------------------------------------------------------------------------------- /.github/workflows/push-image.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/.github/workflows/push-image.yml -------------------------------------------------------------------------------- /.github/workflows/quality.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/.github/workflows/quality.yml -------------------------------------------------------------------------------- /.github/workflows/tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/.github/workflows/tests.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/.gitignore -------------------------------------------------------------------------------- /AGENTS.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/AGENTS.md -------------------------------------------------------------------------------- /CLAUDE.md: -------------------------------------------------------------------------------- 1 | AGENTS.md -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/Dockerfile -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/LICENSE -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/Makefile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/README.md -------------------------------------------------------------------------------- /assets/images/tulu_logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/assets/images/tulu_logo.png -------------------------------------------------------------------------------- /assets/model_licenses/llama_license.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/assets/model_licenses/llama_license.txt -------------------------------------------------------------------------------- /assets/model_licenses/opt_license.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/assets/model_licenses/opt_license.txt -------------------------------------------------------------------------------- /assets/model_licenses/pythia_license.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/assets/model_licenses/pythia_license.txt -------------------------------------------------------------------------------- /assets/model_licenses/tulu_license.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/assets/model_licenses/tulu_license.txt -------------------------------------------------------------------------------- /configs/beaker_configs/alpaca_7B.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/alpaca_7B.yaml -------------------------------------------------------------------------------- /configs/beaker_configs/alpaca_7B_lora.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/alpaca_7B_lora.yaml -------------------------------------------------------------------------------- /configs/beaker_configs/code_api_setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/code_api_setup.sh -------------------------------------------------------------------------------- /configs/beaker_configs/default_dpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/default_dpo.yaml -------------------------------------------------------------------------------- /configs/beaker_configs/default_dpo_multinode.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/default_dpo_multinode.yaml -------------------------------------------------------------------------------- /configs/beaker_configs/default_dpo_multinode_olmo2_1124.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/default_dpo_multinode_olmo2_1124.yaml -------------------------------------------------------------------------------- /configs/beaker_configs/default_dpo_multinode_olmo2_1124_augusta.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/default_dpo_multinode_olmo2_1124_augusta.yaml -------------------------------------------------------------------------------- /configs/beaker_configs/default_eval.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/default_eval.yaml -------------------------------------------------------------------------------- /configs/beaker_configs/default_finetune.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/default_finetune.yaml -------------------------------------------------------------------------------- /configs/beaker_configs/default_finetune_lora_multinode.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/default_finetune_lora_multinode.yaml -------------------------------------------------------------------------------- /configs/beaker_configs/default_finetune_multinode.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/default_finetune_multinode.yaml -------------------------------------------------------------------------------- /configs/beaker_configs/default_finetune_multinode_olmo2_1124.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/default_finetune_multinode_olmo2_1124.yaml -------------------------------------------------------------------------------- /configs/beaker_configs/default_finetune_multinode_olmo2_1124_augusta.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/default_finetune_multinode_olmo2_1124_augusta.yaml -------------------------------------------------------------------------------- /configs/beaker_configs/default_finetune_qlora_multinode.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/default_finetune_qlora_multinode.yaml -------------------------------------------------------------------------------- /configs/beaker_configs/ray_node_setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/ray_node_setup.sh -------------------------------------------------------------------------------- /configs/beaker_configs/run_weight_diff.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/beaker_configs/run_weight_diff.sh -------------------------------------------------------------------------------- /configs/ds_configs/deepspeed_zero2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/ds_configs/deepspeed_zero2.yaml -------------------------------------------------------------------------------- /configs/ds_configs/deepspeed_zero3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/ds_configs/deepspeed_zero3.yaml -------------------------------------------------------------------------------- /configs/ds_configs/stage2_accelerate.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/ds_configs/stage2_accelerate.conf -------------------------------------------------------------------------------- /configs/ds_configs/stage3_no_offloading.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/ds_configs/stage3_no_offloading.conf -------------------------------------------------------------------------------- /configs/ds_configs/stage3_no_offloading_accelerate.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/ds_configs/stage3_no_offloading_accelerate.conf -------------------------------------------------------------------------------- /configs/ds_configs/stage3_offloading.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/ds_configs/stage3_offloading.conf -------------------------------------------------------------------------------- /configs/ds_configs/stage3_offloading_accelerate.conf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/ds_configs/stage3_offloading_accelerate.conf -------------------------------------------------------------------------------- /configs/judge_configs/general_verifier_judge.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/judge_configs/general_verifier_judge.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/default.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/final_best_70b_dpo_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/final_best_70b_dpo_config.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/final_best_8b_dpo_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/final_best_8b_dpo_config.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/mini.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/mini.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/olmo_1b_mix_example.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/olmo_1b_mix_example.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/olmo_7b_17_inst.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/olmo_7b_17_inst.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/tulu3_preview_pref_v3.0.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/tulu3_preview_pref_v3.0.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/tulu3_preview_pref_v3.1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/tulu3_preview_pref_v3.1.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/tulu3_preview_pref_v3.2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/tulu3_preview_pref_v3.2.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/tulu3_preview_pref_v3.3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/tulu3_preview_pref_v3.3.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/tulu3_preview_test_simpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/tulu3_preview_test_simpo.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/tulu_3_preview_test_if_faeze.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/tulu_3_preview_test_if_faeze.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/valpy_dpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/valpy_dpo.yaml -------------------------------------------------------------------------------- /configs/train_configs/dpo/valpy_dpo_mix_new.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/dpo/valpy_dpo_mix_new.yaml -------------------------------------------------------------------------------- /configs/train_configs/olmo2/olmo2_1124_13b_dpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/olmo2/olmo2_1124_13b_dpo.yaml -------------------------------------------------------------------------------- /configs/train_configs/olmo2/olmo2_1124_13b_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/olmo2/olmo2_1124_13b_sft.yaml -------------------------------------------------------------------------------- /configs/train_configs/olmo2/olmo2_1124_32b_dpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/olmo2/olmo2_1124_32b_dpo.yaml -------------------------------------------------------------------------------- /configs/train_configs/olmo2/olmo2_1124_7b_dpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/olmo2/olmo2_1124_7b_dpo.yaml -------------------------------------------------------------------------------- /configs/train_configs/olmo2/olmo2_1124_7b_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/olmo2/olmo2_1124_7b_sft.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/default.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/default.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/mini.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/mini.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/olmo_7b_17_remix_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/olmo_7b_17_remix_sft.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/olmo_7b_17_safe_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/olmo_7b_17_safe_sft.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/olmo_7b_17_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/olmo_7b_17_sft.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/olmo_7b_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/olmo_7b_sft.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/olmoe_preview_mix_v3.1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/olmoe_preview_mix_v3.1.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu2_13b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu2_13b.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu2_70b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu2_70b.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu2_7b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu2_7b.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu2_7b_lora.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu2_7b_lora.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu2_7b_qlora.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu2_7b_qlora.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu2_7b_remix.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu2_7b_remix.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_70b_preview_mix_v3.8-commercial.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_70b_preview_mix_v3.8-commercial.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_70b_preview_mix_v3.8-noncommercial.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_70b_preview_mix_v3.8-noncommercial.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_70b_preview_mix_v3.9-noncommercial.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_70b_preview_mix_v3.9-noncommercial.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_no_robot.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_no_robot.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.0.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.0.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.1.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.10.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.10.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.2.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.3.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.0.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.0.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.1.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.10.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.10.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.11.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.11.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.12.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.12.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.13.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.13.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.14.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.14.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.15.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.15.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.16.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.16.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.17.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.17.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.18.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.18.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.19.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.19.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.2.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.20.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.20.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.21.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.21.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.22.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.22.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.23.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.23.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.24.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.24.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.25.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.25.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.26.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.26.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.27.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.27.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.28.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.28.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.29.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.29.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.3.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.30.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.30.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.31.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.31.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.32.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.32.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.4.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.4.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.5.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.5.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.6.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.6.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.7.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.7.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.8.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.8.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.9.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.x/tulu3_8b_preview_mix_v3.4.9.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.4.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.1.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.1.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.10.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.10.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.11.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.11.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.12.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.12.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.13.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.13.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.2.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.2.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.3.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.4.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.4.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.5.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.5.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.6.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.6.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.7.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.7.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.8.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.8.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.9.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.5.x/llama3.1_8b_preview_mix_v3.5.9.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.6.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.6.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.7.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.7.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.8-commercial.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.8-commercial.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.8-noncommercial.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.8-noncommercial.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_8b_preview_mix_v3.9-noncommercial.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_8b_preview_mix_v3.9-noncommercial.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_L3.1_70b_preview_mix_v3.3.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_L3.1_70b_preview_mix_v3.3.yaml -------------------------------------------------------------------------------- /configs/train_configs/sft/tulu3_L3.1_8b_math_faeze.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/sft/tulu3_L3.1_8b_math_faeze.yaml -------------------------------------------------------------------------------- /configs/train_configs/tulu3/tulu3_dpo_70b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/tulu3/tulu3_dpo_70b.yaml -------------------------------------------------------------------------------- /configs/train_configs/tulu3/tulu3_dpo_8b.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/tulu3/tulu3_dpo_8b.yaml -------------------------------------------------------------------------------- /configs/train_configs/tulu3/tulu3_sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/configs/train_configs/tulu3/tulu3_sft.yaml -------------------------------------------------------------------------------- /decontamination/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/decontamination/README.md -------------------------------------------------------------------------------- /decontamination/index.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/decontamination/index.py -------------------------------------------------------------------------------- /decontamination/search.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/decontamination/search.py -------------------------------------------------------------------------------- /docs/ai2_internal.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/ai2_internal.md -------------------------------------------------------------------------------- /docs/algorithms/dataset/sft.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dataset/sft.png -------------------------------------------------------------------------------- /docs/algorithms/dataset/sft2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dataset/sft2.png -------------------------------------------------------------------------------- /docs/algorithms/dataset_transformation.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dataset_transformation.md -------------------------------------------------------------------------------- /docs/algorithms/dpo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dpo.md -------------------------------------------------------------------------------- /docs/algorithms/dpo/olmo2_13b_dpo-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dpo/olmo2_13b_dpo-time.png -------------------------------------------------------------------------------- /docs/algorithms/dpo/olmo2_13b_dpo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dpo/olmo2_13b_dpo.png -------------------------------------------------------------------------------- /docs/algorithms/dpo/olmo2_13b_dpo_eval.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dpo/olmo2_13b_dpo_eval.png -------------------------------------------------------------------------------- /docs/algorithms/dpo/olmo2_7b_dpo-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dpo/olmo2_7b_dpo-time.png -------------------------------------------------------------------------------- /docs/algorithms/dpo/olmo2_7b_dpo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dpo/olmo2_7b_dpo.png -------------------------------------------------------------------------------- /docs/algorithms/dpo/olmo2_7b_dpo_eval.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dpo/olmo2_7b_dpo_eval.png -------------------------------------------------------------------------------- /docs/algorithms/dpo/tulu3_8b_dpo-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dpo/tulu3_8b_dpo-time.png -------------------------------------------------------------------------------- /docs/algorithms/dpo/tulu3_8b_dpo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dpo/tulu3_8b_dpo.png -------------------------------------------------------------------------------- /docs/algorithms/dpo/tulu3_8b_dpo_eval.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dpo/tulu3_8b_dpo_eval.png -------------------------------------------------------------------------------- /docs/algorithms/dpo/tulu3_8b_dpo_eval_drop.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/dpo/tulu3_8b_dpo_eval_drop.png -------------------------------------------------------------------------------- /docs/algorithms/finetune.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune.md -------------------------------------------------------------------------------- /docs/algorithms/finetune/finetune_debug.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune/finetune_debug.png -------------------------------------------------------------------------------- /docs/algorithms/finetune/olmo2_13b_sft-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune/olmo2_13b_sft-time.png -------------------------------------------------------------------------------- /docs/algorithms/finetune/olmo2_13b_sft.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune/olmo2_13b_sft.png -------------------------------------------------------------------------------- /docs/algorithms/finetune/olmo2_32b_sft-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune/olmo2_32b_sft-time.png -------------------------------------------------------------------------------- /docs/algorithms/finetune/olmo2_32b_sft.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune/olmo2_32b_sft.png -------------------------------------------------------------------------------- /docs/algorithms/finetune/olmo2_32b_sft_eval.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune/olmo2_32b_sft_eval.png -------------------------------------------------------------------------------- /docs/algorithms/finetune/olmo2_7b_sft-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune/olmo2_7b_sft-time.png -------------------------------------------------------------------------------- /docs/algorithms/finetune/olmo2_7b_sft.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune/olmo2_7b_sft.png -------------------------------------------------------------------------------- /docs/algorithms/finetune/olmo2_7b_sft_eval.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune/olmo2_7b_sft_eval.png -------------------------------------------------------------------------------- /docs/algorithms/finetune/tulu3_8b.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune/tulu3_8b.png -------------------------------------------------------------------------------- /docs/algorithms/finetune/tulu3_8b_eval.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune/tulu3_8b_eval.png -------------------------------------------------------------------------------- /docs/algorithms/finetune/tulu3_8b_sft-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune/tulu3_8b_sft-time.png -------------------------------------------------------------------------------- /docs/algorithms/finetune/tulu3_8b_sft.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/finetune/tulu3_8b_sft.png -------------------------------------------------------------------------------- /docs/algorithms/grpo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo.md -------------------------------------------------------------------------------- /docs/algorithms/grpo/additive_format_reward.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/additive_format_reward.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/grpo_fast_gradient.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/grpo_fast_gradient.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/olmo2_13b_grpo_fast_zero-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/olmo2_13b_grpo_fast_zero-time.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/olmo2_13b_grpo_fast_zero.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/olmo2_13b_grpo_fast_zero.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/olmo2_13b_grpo_fast_zero_eval_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/olmo2_13b_grpo_fast_zero_eval_curve.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/olmo2_7b_grpo-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/olmo2_7b_grpo-time.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/olmo2_7b_grpo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/olmo2_7b_grpo.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/olmo2_7b_grpo_eval.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/olmo2_7b_grpo_eval.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/olmo2_7b_grpo_eval_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/olmo2_7b_grpo_eval_curve.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/olmo2_7b_grpo_fast_zero-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/olmo2_7b_grpo_fast_zero-time.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/olmo2_7b_grpo_fast_zero.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/olmo2_7b_grpo_fast_zero.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/olmo2_7b_grpo_fast_zero_eval_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/olmo2_7b_grpo_fast_zero_eval_curve.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/qwen2.5_7b_grpo_fast_zero-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/qwen2.5_7b_grpo_fast_zero-time.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/qwen2.5_7b_grpo_fast_zero.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/qwen2.5_7b_grpo_fast_zero.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/qwen2.5_7b_grpo_fast_zero_eval_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/qwen2.5_7b_grpo_fast_zero_eval_curve.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/qwen2.5_7b_grpo_zero-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/qwen2.5_7b_grpo_zero-time.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/qwen2.5_7b_grpo_zero.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/qwen2.5_7b_grpo_zero.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/qwen2.5_7b_grpo_zero_eval_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/qwen2.5_7b_grpo_zero_eval_curve.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/tulu3.1_8b_grpo-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/tulu3.1_8b_grpo-time.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/tulu3.1_8b_grpo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/tulu3.1_8b_grpo.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/tulu3.1_8b_grpo_eval.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/tulu3.1_8b_grpo_eval.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/tulu3.1_8b_grpo_eval_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/tulu3.1_8b_grpo_eval_curve.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/tulu3.1_8b_grpo_fast-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/tulu3.1_8b_grpo_fast-time.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/tulu3.1_8b_grpo_fast.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/tulu3.1_8b_grpo_fast.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/tulu3.1_8b_grpo_fast_eval.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/tulu3.1_8b_grpo_fast_eval.png -------------------------------------------------------------------------------- /docs/algorithms/grpo/tulu3.1_8b_grpo_fast_eval_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo/tulu3.1_8b_grpo_fast_eval_curve.png -------------------------------------------------------------------------------- /docs/algorithms/grpo_8b.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/grpo_8b.png -------------------------------------------------------------------------------- /docs/algorithms/online_dpo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/online_dpo.md -------------------------------------------------------------------------------- /docs/algorithms/plot/finetune_plot.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/plot/finetune_plot.sh -------------------------------------------------------------------------------- /docs/algorithms/ppo.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/ppo.md -------------------------------------------------------------------------------- /docs/algorithms/rejection_sampling.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/rejection_sampling.md -------------------------------------------------------------------------------- /docs/algorithms/reward_modeling.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/reward_modeling.md -------------------------------------------------------------------------------- /docs/algorithms/reward_modeling/tulu3_8b_rm-time.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/reward_modeling/tulu3_8b_rm-time.png -------------------------------------------------------------------------------- /docs/algorithms/reward_modeling/tulu3_8b_rm.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/reward_modeling/tulu3_8b_rm.png -------------------------------------------------------------------------------- /docs/algorithms/reward_modeling_colored_tokens.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/reward_modeling_colored_tokens.png -------------------------------------------------------------------------------- /docs/algorithms/reward_modeling_ds.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/reward_modeling_ds.png -------------------------------------------------------------------------------- /docs/algorithms/reward_modeling_hf_repo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/reward_modeling_hf_repo.png -------------------------------------------------------------------------------- /docs/algorithms/reward_modeling_hf_viz.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/reward_modeling_hf_viz.png -------------------------------------------------------------------------------- /docs/algorithms/reward_modeling_preference_sample_texts.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/reward_modeling_preference_sample_texts.png -------------------------------------------------------------------------------- /docs/algorithms/reward_modeling_token.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/reward_modeling_token.png -------------------------------------------------------------------------------- /docs/algorithms/reward_modeling_token_wandb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/reward_modeling_token_wandb.png -------------------------------------------------------------------------------- /docs/algorithms/static/grpo_qwen2.5_7B_works.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/static/grpo_qwen2.5_7B_works.png -------------------------------------------------------------------------------- /docs/algorithms/static/grpo_qwen2.5_7B_works_evals.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/static/grpo_qwen2.5_7B_works_evals.png -------------------------------------------------------------------------------- /docs/algorithms/static/grpo_qwen_fast_2.5_7B.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/static/grpo_qwen_fast_2.5_7B.png -------------------------------------------------------------------------------- /docs/algorithms/synthetic_preference_dataset.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/synthetic_preference_dataset.md -------------------------------------------------------------------------------- /docs/algorithms/synthetic_preference_dataset.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/synthetic_preference_dataset.png -------------------------------------------------------------------------------- /docs/algorithms/trained_model_location.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/trained_model_location.md -------------------------------------------------------------------------------- /docs/algorithms/trained_model_location/beaker_dataset.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/trained_model_location/beaker_dataset.gif -------------------------------------------------------------------------------- /docs/algorithms/trained_model_location/gsc.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/trained_model_location/gsc.png -------------------------------------------------------------------------------- /docs/algorithms/trained_model_location/hf.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/trained_model_location/hf.png -------------------------------------------------------------------------------- /docs/algorithms/trained_model_location/hf2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/trained_model_location/hf2.png -------------------------------------------------------------------------------- /docs/algorithms/trained_model_location/local.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/algorithms/trained_model_location/local.png -------------------------------------------------------------------------------- /docs/archived_dev_scripts/olmo2_1124.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/archived_dev_scripts/olmo2_1124.sh -------------------------------------------------------------------------------- /docs/archived_dev_scripts/olmoe_0125.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/archived_dev_scripts/olmoe_0125.sh -------------------------------------------------------------------------------- /docs/assets/favicon.ico: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/assets/favicon.ico -------------------------------------------------------------------------------- /docs/assets/images/tulu_logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/assets/images/tulu_logo.png -------------------------------------------------------------------------------- /docs/data/preference-data.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/data/preference-data.md -------------------------------------------------------------------------------- /docs/get_started/ai2_internal_setup.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/get_started/ai2_internal_setup.md -------------------------------------------------------------------------------- /docs/get_started/installation.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/get_started/installation.md -------------------------------------------------------------------------------- /docs/get_started/internal_leaderboard.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/get_started/internal_leaderboard.png -------------------------------------------------------------------------------- /docs/get_started/mason.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/get_started/mason.png -------------------------------------------------------------------------------- /docs/get_started/mason_job.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/get_started/mason_job.png -------------------------------------------------------------------------------- /docs/get_started/vscode.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/get_started/vscode.png -------------------------------------------------------------------------------- /docs/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/index.md -------------------------------------------------------------------------------- /docs/olmo2.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/olmo2.md -------------------------------------------------------------------------------- /docs/safety-eval/safety.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/safety-eval/safety.md -------------------------------------------------------------------------------- /docs/safety.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/safety.md -------------------------------------------------------------------------------- /docs/stylesheets/extra.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/stylesheets/extra.css -------------------------------------------------------------------------------- /docs/tulu1_tulu2.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/tulu1_tulu2.md -------------------------------------------------------------------------------- /docs/tulu3.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/docs/tulu3.md -------------------------------------------------------------------------------- /human_eval/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/human_eval/README.md -------------------------------------------------------------------------------- /human_eval/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/human_eval/app.py -------------------------------------------------------------------------------- /human_eval/compute_metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/human_eval/compute_metrics.py -------------------------------------------------------------------------------- /human_eval/data/eval_annotations_tulu_1.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/human_eval/data/eval_annotations_tulu_1.xlsx -------------------------------------------------------------------------------- /human_eval/data/eval_instances_tulu_1.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/human_eval/data/eval_instances_tulu_1.jsonl -------------------------------------------------------------------------------- /human_eval/export_db.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/human_eval/export_db.py -------------------------------------------------------------------------------- /human_eval/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/human_eval/requirements.txt -------------------------------------------------------------------------------- /human_eval/screenshot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/human_eval/screenshot.png -------------------------------------------------------------------------------- /human_eval/static/app.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/human_eval/static/app.js -------------------------------------------------------------------------------- /human_eval/static/favicon.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/human_eval/static/favicon.png -------------------------------------------------------------------------------- /human_eval/static/styles.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/human_eval/static/styles.css -------------------------------------------------------------------------------- /human_eval/templates/index.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/human_eval/templates/index.html -------------------------------------------------------------------------------- /human_eval/templates/login.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/human_eval/templates/login.html -------------------------------------------------------------------------------- /mason.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/mason.py -------------------------------------------------------------------------------- /mkdocs.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/mkdocs.yml -------------------------------------------------------------------------------- /open_instruct/IFEvalG/instructions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/IFEvalG/instructions.py -------------------------------------------------------------------------------- /open_instruct/IFEvalG/instructions_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/IFEvalG/instructions_registry.py -------------------------------------------------------------------------------- /open_instruct/IFEvalG/instructions_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/IFEvalG/instructions_util.py -------------------------------------------------------------------------------- /open_instruct/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /open_instruct/actor_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/actor_manager.py -------------------------------------------------------------------------------- /open_instruct/benchmark_generators.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/benchmark_generators.py -------------------------------------------------------------------------------- /open_instruct/code_utils/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/code_utils/Dockerfile -------------------------------------------------------------------------------- /open_instruct/code_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/code_utils/__init__.py -------------------------------------------------------------------------------- /open_instruct/code_utils/api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/code_utils/api.py -------------------------------------------------------------------------------- /open_instruct/code_utils/code_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/code_utils/code_utils.py -------------------------------------------------------------------------------- /open_instruct/code_utils/test_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/code_utils/test_api.py -------------------------------------------------------------------------------- /open_instruct/code_utils/test_code_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/code_utils/test_code_utils.py -------------------------------------------------------------------------------- /open_instruct/code_utils/testing_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/code_utils/testing_util.py -------------------------------------------------------------------------------- /open_instruct/context_window_checker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/context_window_checker.py -------------------------------------------------------------------------------- /open_instruct/data_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/data_loader.py -------------------------------------------------------------------------------- /open_instruct/data_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/data_types.py -------------------------------------------------------------------------------- /open_instruct/dataset_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/dataset_processor.py -------------------------------------------------------------------------------- /open_instruct/dataset_transformation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/dataset_transformation.py -------------------------------------------------------------------------------- /open_instruct/dpo_tune_cache.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/dpo_tune_cache.py -------------------------------------------------------------------------------- /open_instruct/dpo_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/dpo_utils.py -------------------------------------------------------------------------------- /open_instruct/experimental/oai_generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/experimental/oai_generate.py -------------------------------------------------------------------------------- /open_instruct/experimental/test.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/experimental/test.jsonl -------------------------------------------------------------------------------- /open_instruct/finetune.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/finetune.py -------------------------------------------------------------------------------- /open_instruct/ground_truth_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/ground_truth_utils.py -------------------------------------------------------------------------------- /open_instruct/grpo_fast.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/grpo_fast.py -------------------------------------------------------------------------------- /open_instruct/if_functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/if_functions.py -------------------------------------------------------------------------------- /open_instruct/judge_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/judge_utils.py -------------------------------------------------------------------------------- /open_instruct/logger_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/logger_utils.py -------------------------------------------------------------------------------- /open_instruct/math_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/math_utils.py -------------------------------------------------------------------------------- /open_instruct/merge_lora.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/merge_lora.py -------------------------------------------------------------------------------- /open_instruct/mix_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/mix_data.py -------------------------------------------------------------------------------- /open_instruct/mix_data_preferences.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/mix_data_preferences.py -------------------------------------------------------------------------------- /open_instruct/model_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/model_utils.py -------------------------------------------------------------------------------- /open_instruct/olmo_adapter/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/olmo_adapter/__init__.py -------------------------------------------------------------------------------- /open_instruct/padding_free_collator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/padding_free_collator.py -------------------------------------------------------------------------------- /open_instruct/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/ppo.py -------------------------------------------------------------------------------- /open_instruct/rejection_sampling/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /open_instruct/rejection_sampling/api_generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/rejection_sampling/api_generate.py -------------------------------------------------------------------------------- /open_instruct/rejection_sampling/generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/rejection_sampling/generation.py -------------------------------------------------------------------------------- /open_instruct/rejection_sampling/prompt_templates.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/rejection_sampling/prompt_templates.py -------------------------------------------------------------------------------- /open_instruct/rejection_sampling/rejection_sampling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/rejection_sampling/rejection_sampling.py -------------------------------------------------------------------------------- /open_instruct/rejection_sampling/synthetic_preference_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/rejection_sampling/synthetic_preference_dataset.py -------------------------------------------------------------------------------- /open_instruct/reward_modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/reward_modeling.py -------------------------------------------------------------------------------- /open_instruct/reward_modeling_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/reward_modeling_eval.py -------------------------------------------------------------------------------- /open_instruct/rl_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/rl_utils.py -------------------------------------------------------------------------------- /open_instruct/search_utils/massive_ds.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/search_utils/massive_ds.py -------------------------------------------------------------------------------- /open_instruct/search_utils/s2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/search_utils/s2.py -------------------------------------------------------------------------------- /open_instruct/search_utils/search_tool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/search_utils/search_tool.py -------------------------------------------------------------------------------- /open_instruct/search_utils/you.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/search_utils/you.py -------------------------------------------------------------------------------- /open_instruct/static/dashboard.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/static/dashboard.css -------------------------------------------------------------------------------- /open_instruct/static/dashboard.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/static/dashboard.html -------------------------------------------------------------------------------- /open_instruct/test_benchmark_generators.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/test_benchmark_generators.py -------------------------------------------------------------------------------- /open_instruct/test_data/mbu_reproduction_cases.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/test_data/mbu_reproduction_cases.json -------------------------------------------------------------------------------- /open_instruct/test_data_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/test_data_loader.py -------------------------------------------------------------------------------- /open_instruct/test_dataset_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/test_dataset_processor.py -------------------------------------------------------------------------------- /open_instruct/test_dataset_transformation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/test_dataset_transformation.py -------------------------------------------------------------------------------- /open_instruct/test_ground_truth_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/test_ground_truth_utils.py -------------------------------------------------------------------------------- /open_instruct/test_grpo_fast.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/test_grpo_fast.py -------------------------------------------------------------------------------- /open_instruct/test_math_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/test_math_utils.py -------------------------------------------------------------------------------- /open_instruct/test_model_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/test_model_utils.py -------------------------------------------------------------------------------- /open_instruct/test_padding_free_collator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/test_padding_free_collator.py -------------------------------------------------------------------------------- /open_instruct/test_rl_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/test_rl_utils.py -------------------------------------------------------------------------------- /open_instruct/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/test_utils.py -------------------------------------------------------------------------------- /open_instruct/test_vllm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/test_vllm_utils.py -------------------------------------------------------------------------------- /open_instruct/tool_utils/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/tool_utils/Dockerfile -------------------------------------------------------------------------------- /open_instruct/tool_utils/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/tool_utils/requirements.txt -------------------------------------------------------------------------------- /open_instruct/tool_utils/test_tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/tool_utils/test_tools.py -------------------------------------------------------------------------------- /open_instruct/tool_utils/tool_server.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/tool_utils/tool_server.py -------------------------------------------------------------------------------- /open_instruct/tool_utils/tools.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/tool_utils/tools.py -------------------------------------------------------------------------------- /open_instruct/tools/system_prompts/debug_system_prompt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/tools/system_prompts/debug_system_prompt.txt -------------------------------------------------------------------------------- /open_instruct/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/utils.py -------------------------------------------------------------------------------- /open_instruct/vllm_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/vllm_utils.py -------------------------------------------------------------------------------- /open_instruct/vllm_utils_workerwrap.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/open_instruct/vllm_utils_workerwrap.py -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/pyproject.toml -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/requirements.txt -------------------------------------------------------------------------------- /scripts/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/README.md -------------------------------------------------------------------------------- /scripts/add_metadata.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/add_metadata.py -------------------------------------------------------------------------------- /scripts/add_metadata_from_wandb.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/add_metadata_from_wandb.py -------------------------------------------------------------------------------- /scripts/benchmarking/launch_benchmark_single_gpu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/benchmarking/launch_benchmark_single_gpu.sh -------------------------------------------------------------------------------- /scripts/benchmarking/launch_benchmark_single_node.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/benchmarking/launch_benchmark_single_node.sh -------------------------------------------------------------------------------- /scripts/benchmarking/olmo3_infra.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/benchmarking/olmo3_infra.sh -------------------------------------------------------------------------------- /scripts/cache_hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/cache_hf.py -------------------------------------------------------------------------------- /scripts/collect_eval_results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/collect_eval_results.py -------------------------------------------------------------------------------- /scripts/convert_olmo_1124_weights_to_hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/convert_olmo_1124_weights_to_hf.py -------------------------------------------------------------------------------- /scripts/create_ground_truth_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/create_ground_truth_data.py -------------------------------------------------------------------------------- /scripts/data/azure_batch/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/azure_batch/README.md -------------------------------------------------------------------------------- /scripts/data/azure_batch/check_azure_batch_status.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/azure_batch/check_azure_batch_status.py -------------------------------------------------------------------------------- /scripts/data/azure_batch/process_azure_batch_results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/azure_batch/process_azure_batch_results.py -------------------------------------------------------------------------------- /scripts/data/azure_batch/regenerate_dataset_completions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/azure_batch/regenerate_dataset_completions.py -------------------------------------------------------------------------------- /scripts/data/build_hardcoded.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/build_hardcoded.py -------------------------------------------------------------------------------- /scripts/data/convert_general_thought_to_tulu_thinker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/convert_general_thought_to_tulu_thinker.py -------------------------------------------------------------------------------- /scripts/data/convert_sft_data_for_olmocore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/convert_sft_data_for_olmocore.py -------------------------------------------------------------------------------- /scripts/data/create_deepscaler_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/create_deepscaler_data.py -------------------------------------------------------------------------------- /scripts/data/create_gpqa_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/create_gpqa_data.py -------------------------------------------------------------------------------- /scripts/data/create_long_form_qa_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/create_long_form_qa_data.py -------------------------------------------------------------------------------- /scripts/data/create_nq_tqa_hotpotqa_2wiki_simplqa_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/create_nq_tqa_hotpotqa_2wiki_simplqa_data.py -------------------------------------------------------------------------------- /scripts/data/create_thinker_tulu_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/create_thinker_tulu_data.py -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/README.md -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/TEST_README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/TEST_README.md -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/filter_chinese.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/filter_chinese.py -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/filter_chinese_batch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/filter_chinese_batch.sh -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/filter_cots.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/filter_cots.py -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/filter_cutoff_date.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/filter_cutoff_date.py -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/filter_dataset_by_keywords.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/filter_dataset_by_keywords.py -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/filter_datasets_sequential.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/filter_datasets_sequential.sh -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/filter_ngram_repetitions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/filter_ngram_repetitions.py -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/filter_repetition.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/filter_repetition.sh -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/filter_special_tokens.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/filter_special_tokens.py -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/filter_wildchat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/filter_wildchat.py -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/run_tests.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/run_tests.py -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/test_filter_ngram_repetitions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/test_filter_ngram_repetitions.py -------------------------------------------------------------------------------- /scripts/data/filtering_and_updates/update_subsets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/filtering_and_updates/update_subsets.py -------------------------------------------------------------------------------- /scripts/data/finetune_dataset_transformation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/finetune_dataset_transformation.py -------------------------------------------------------------------------------- /scripts/data/get_statistics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/get_statistics.py -------------------------------------------------------------------------------- /scripts/data/get_statistics_tulu_v3.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/get_statistics_tulu_v3.sh -------------------------------------------------------------------------------- /scripts/data/get_token_distribution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/get_token_distribution.py -------------------------------------------------------------------------------- /scripts/data/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/gsm8k.py -------------------------------------------------------------------------------- /scripts/data/make_eurus2_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/make_eurus2_data.py -------------------------------------------------------------------------------- /scripts/data/preferences/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/data/preferences/dataset_info.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/preferences/dataset_info.py -------------------------------------------------------------------------------- /scripts/data/preferences/helpsteer2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/preferences/helpsteer2.py -------------------------------------------------------------------------------- /scripts/data/preferences/helpsteer2_nvidia.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/preferences/helpsteer2_nvidia.py -------------------------------------------------------------------------------- /scripts/data/preferences/hh-harmless.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/preferences/hh-harmless.py -------------------------------------------------------------------------------- /scripts/data/preferences/hh-helpful.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/preferences/hh-helpful.py -------------------------------------------------------------------------------- /scripts/data/preferences/nectar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/preferences/nectar.py -------------------------------------------------------------------------------- /scripts/data/preferences/prepare_all.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/preferences/prepare_all.sh -------------------------------------------------------------------------------- /scripts/data/preferences/split_tulu2.5_prefs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/preferences/split_tulu2.5_prefs.py -------------------------------------------------------------------------------- /scripts/data/preferences/ultrafeedback_replications.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/preferences/ultrafeedback_replications.py -------------------------------------------------------------------------------- /scripts/data/preferences/ultrainteract.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/preferences/ultrainteract.py -------------------------------------------------------------------------------- /scripts/data/preferences/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/preferences/utils.py -------------------------------------------------------------------------------- /scripts/data/preferences/webgpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/preferences/webgpt.py -------------------------------------------------------------------------------- /scripts/data/read_statistics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/read_statistics.py -------------------------------------------------------------------------------- /scripts/data/rlvr/acecoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr/acecoder.py -------------------------------------------------------------------------------- /scripts/data/rlvr/filter_existing_dataset_correctness.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr/filter_existing_dataset_correctness.py -------------------------------------------------------------------------------- /scripts/data/rlvr/filtering_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr/filtering_vllm.py -------------------------------------------------------------------------------- /scripts/data/rlvr/gsm8k_rlvr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr/gsm8k_rlvr.py -------------------------------------------------------------------------------- /scripts/data/rlvr/open_reasoner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr/open_reasoner.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/code_create_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/code_create_batch.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/code_create_batch_solution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/code_create_batch_solution.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/code_create_batch_stdio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/code_create_batch_stdio.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/code_create_batch_translate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/code_create_batch_translate.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/code_upload_batch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/code_upload_batch.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/code_upload_batch_difficulty.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/code_upload_batch_difficulty.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/code_upload_batch_stdio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/code_upload_batch_stdio.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/code_upload_batch_translate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/code_upload_batch_translate.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/filter_seq_len.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/filter_seq_len.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/grade_difficulty.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/grade_difficulty.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/plot_seq_len.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/plot_seq_len.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/rlvr_to_sft.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/rlvr_to_sft.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/sft_to_rlvr_azure.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/sft_to_rlvr_azure.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/the_algorithms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/the_algorithms.py -------------------------------------------------------------------------------- /scripts/data/rlvr_code/verify_qwq.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/rlvr_code/verify_qwq.py -------------------------------------------------------------------------------- /scripts/data/scripts/data/create_asqa_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/scripts/data/create_asqa_data.py -------------------------------------------------------------------------------- /scripts/data/sft/aya.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/aya.py -------------------------------------------------------------------------------- /scripts/data/sft/coconot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/coconot.py -------------------------------------------------------------------------------- /scripts/data/sft/codefeedback_mix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/codefeedback_mix.py -------------------------------------------------------------------------------- /scripts/data/sft/daring_anteater.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/daring_anteater.py -------------------------------------------------------------------------------- /scripts/data/sft/evol_codealpaca.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/evol_codealpaca.py -------------------------------------------------------------------------------- /scripts/data/sft/flan.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/flan.py -------------------------------------------------------------------------------- /scripts/data/sft/lima.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/lima.py -------------------------------------------------------------------------------- /scripts/data/sft/llama_nemotron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/llama_nemotron.py -------------------------------------------------------------------------------- /scripts/data/sft/lmsys_chat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/lmsys_chat.py -------------------------------------------------------------------------------- /scripts/data/sft/metamath.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/metamath.py -------------------------------------------------------------------------------- /scripts/data/sft/no_robots.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/no_robots.py -------------------------------------------------------------------------------- /scripts/data/sft/numinamath.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/numinamath.py -------------------------------------------------------------------------------- /scripts/data/sft/open_assistant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/open_assistant.py -------------------------------------------------------------------------------- /scripts/data/sft/open_code_reasoner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/open_code_reasoner.py -------------------------------------------------------------------------------- /scripts/data/sft/open_math_instruct.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/open_math_instruct.py -------------------------------------------------------------------------------- /scripts/data/sft/prepare_all.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/prepare_all.sh -------------------------------------------------------------------------------- /scripts/data/sft/sciriff.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/sciriff.py -------------------------------------------------------------------------------- /scripts/data/sft/sharegpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/sharegpt.py -------------------------------------------------------------------------------- /scripts/data/sft/slim_orca.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/slim_orca.py -------------------------------------------------------------------------------- /scripts/data/sft/table_gpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/table_gpt.py -------------------------------------------------------------------------------- /scripts/data/sft/tulu_hard_coded.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/tulu_hard_coded.py -------------------------------------------------------------------------------- /scripts/data/sft/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/utils.py -------------------------------------------------------------------------------- /scripts/data/sft/web_instruct.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/web_instruct.py -------------------------------------------------------------------------------- /scripts/data/sft/wildchat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/wildchat.py -------------------------------------------------------------------------------- /scripts/data/sft/wizardlm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft/wizardlm.py -------------------------------------------------------------------------------- /scripts/data/sft_v1_v2/get_statistics.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft_v1_v2/get_statistics.sh -------------------------------------------------------------------------------- /scripts/data/sft_v1_v2/prepare_science_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft_v1_v2/prepare_science_data.py -------------------------------------------------------------------------------- /scripts/data/sft_v1_v2/prepare_tulu_v1_v2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft_v1_v2/prepare_tulu_v1_v2.sh -------------------------------------------------------------------------------- /scripts/data/sft_v1_v2/reformat_datasets.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft_v1_v2/reformat_datasets.py -------------------------------------------------------------------------------- /scripts/data/sft_v1_v2/resample_flan_v2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft_v1_v2/resample_flan_v2.py -------------------------------------------------------------------------------- /scripts/data/sft_v1_v2/split_sharegpt_conversations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/data/sft_v1_v2/split_sharegpt_conversations.py -------------------------------------------------------------------------------- /scripts/does_prompt_make_sense.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/does_prompt_make_sense.py -------------------------------------------------------------------------------- /scripts/dpo_train_with_accelerate.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/dpo_train_with_accelerate.sh -------------------------------------------------------------------------------- /scripts/dpo_train_with_accelerate_config.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/dpo_train_with_accelerate_config.sh -------------------------------------------------------------------------------- /scripts/dpo_train_with_qlora.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/dpo_train_with_qlora.sh -------------------------------------------------------------------------------- /scripts/eval/MATH.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/MATH.sh -------------------------------------------------------------------------------- /scripts/eval/alpaca_farm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/alpaca_farm.sh -------------------------------------------------------------------------------- /scripts/eval/bbh.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/bbh.sh -------------------------------------------------------------------------------- /scripts/eval/bfcl_supported_models.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/bfcl_supported_models.sh -------------------------------------------------------------------------------- /scripts/eval/codex_humaneval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/codex_humaneval.sh -------------------------------------------------------------------------------- /scripts/eval/dummy_length_scorer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/dummy_length_scorer.py -------------------------------------------------------------------------------- /scripts/eval/faster_oe_eval_mmlu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/faster_oe_eval_mmlu.sh -------------------------------------------------------------------------------- /scripts/eval/fetch_mmlu_jobs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/fetch_mmlu_jobs.py -------------------------------------------------------------------------------- /scripts/eval/gsm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/gsm.sh -------------------------------------------------------------------------------- /scripts/eval/ifeval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/ifeval.sh -------------------------------------------------------------------------------- /scripts/eval/mbpp.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/mbpp.sh -------------------------------------------------------------------------------- /scripts/eval/mmlu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/mmlu.sh -------------------------------------------------------------------------------- /scripts/eval/oe-eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/oe-eval.sh -------------------------------------------------------------------------------- /scripts/eval/toxigen.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/toxigen.sh -------------------------------------------------------------------------------- /scripts/eval/truthfulqa.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/truthfulqa.sh -------------------------------------------------------------------------------- /scripts/eval/tulu3_baselines.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/tulu3_baselines.sh -------------------------------------------------------------------------------- /scripts/eval/tulu3_baselines_unseen.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/tulu3_baselines_unseen.sh -------------------------------------------------------------------------------- /scripts/eval/tydiqa.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/tydiqa.sh -------------------------------------------------------------------------------- /scripts/eval/xstest.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval/xstest.sh -------------------------------------------------------------------------------- /scripts/eval_constraints/if_functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/eval_constraints/if_functions.py -------------------------------------------------------------------------------- /scripts/export_chat_template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/export_chat_template.py -------------------------------------------------------------------------------- /scripts/finetune_lora_with_accelerate.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/finetune_lora_with_accelerate.sh -------------------------------------------------------------------------------- /scripts/finetune_lora_with_accelerate_config.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/finetune_lora_with_accelerate_config.sh -------------------------------------------------------------------------------- /scripts/finetune_qlora_with_accelerate.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/finetune_qlora_with_accelerate.sh -------------------------------------------------------------------------------- /scripts/finetune_qlora_with_accelerate_config.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/finetune_qlora_with_accelerate_config.sh -------------------------------------------------------------------------------- /scripts/finetune_with_accelerate.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/finetune_with_accelerate.sh -------------------------------------------------------------------------------- /scripts/finetune_with_accelerate_config.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/finetune_with_accelerate_config.sh -------------------------------------------------------------------------------- /scripts/persona_driven_data_gen/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/persona_driven_data_gen/README.md -------------------------------------------------------------------------------- /scripts/persona_driven_data_gen/data/if_constraint_fewshots_handwritten.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/persona_driven_data_gen/data/if_constraint_fewshots_handwritten.json -------------------------------------------------------------------------------- /scripts/persona_driven_data_gen/persona_driven_generate_ifdata.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/persona_driven_data_gen/persona_driven_generate_ifdata.py -------------------------------------------------------------------------------- /scripts/persona_driven_data_gen/persona_driven_generate_math_code.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/persona_driven_data_gen/persona_driven_generate_math_code.py -------------------------------------------------------------------------------- /scripts/persona_driven_data_gen/prompt_templates.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/persona_driven_data_gen/prompt_templates.py -------------------------------------------------------------------------------- /scripts/persona_driven_data_gen/requirements.txt: -------------------------------------------------------------------------------- 1 | anthropic 2 | openai==0.28 3 | tenacity 4 | -------------------------------------------------------------------------------- /scripts/rejection_sampling_tulu.bash: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/rejection_sampling_tulu.bash -------------------------------------------------------------------------------- /scripts/rejection_sampling_tulu_docker.bash: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/rejection_sampling_tulu_docker.bash -------------------------------------------------------------------------------- /scripts/submit_dpo_job.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/submit_dpo_job.py -------------------------------------------------------------------------------- /scripts/submit_eval_jobs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/submit_eval_jobs.py -------------------------------------------------------------------------------- /scripts/submit_finetune_job.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/submit_finetune_job.py -------------------------------------------------------------------------------- /scripts/submit_finetune_jobs.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/submit_finetune_jobs.sh -------------------------------------------------------------------------------- /scripts/synth_pref/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/README.md -------------------------------------------------------------------------------- /scripts/synth_pref/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/synth_pref/annotate_preferences.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/annotate_preferences.py -------------------------------------------------------------------------------- /scripts/synth_pref/assets/ufpp_pipeline_v2_code.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/assets/ufpp_pipeline_v2_code.png -------------------------------------------------------------------------------- /scripts/synth_pref/assets/ufpp_pipeline_v2_normal.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/assets/ufpp_pipeline_v2_normal.png -------------------------------------------------------------------------------- /scripts/synth_pref/create_annotation_mix.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/create_annotation_mix.py -------------------------------------------------------------------------------- /scripts/synth_pref/example/create_annotation_mix_out/full/helpfulness-full.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/example/create_annotation_mix_out/full/helpfulness-full.jsonl -------------------------------------------------------------------------------- /scripts/synth_pref/example/create_annotation_mix_out/full/honesty-full.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/example/create_annotation_mix_out/full/honesty-full.jsonl -------------------------------------------------------------------------------- /scripts/synth_pref/example/create_annotation_mix_out/full/instruction_following-full.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/example/create_annotation_mix_out/full/instruction_following-full.jsonl -------------------------------------------------------------------------------- /scripts/synth_pref/example/create_annotation_mix_out/full/truthfulness-full.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/example/create_annotation_mix_out/full/truthfulness-full.jsonl -------------------------------------------------------------------------------- /scripts/synth_pref/example/create_annotation_mix_out/myprompts/helpfulness/helpfulness___shard-000000.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/example/create_annotation_mix_out/myprompts/helpfulness/helpfulness___shard-000000.jsonl -------------------------------------------------------------------------------- /scripts/synth_pref/example/create_annotation_mix_out/myprompts/honesty/honesty___shard-000000.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/example/create_annotation_mix_out/myprompts/honesty/honesty___shard-000000.jsonl -------------------------------------------------------------------------------- /scripts/synth_pref/example/create_annotation_mix_out/myprompts/instruction_following/instruction_following___shard-000000.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/example/create_annotation_mix_out/myprompts/instruction_following/instruction_following___shard-000000.jsonl -------------------------------------------------------------------------------- /scripts/synth_pref/example/create_annotation_mix_out/myprompts/truthfulness/truthfulness___shard-000000.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/example/create_annotation_mix_out/myprompts/truthfulness/truthfulness___shard-000000.jsonl -------------------------------------------------------------------------------- /scripts/synth_pref/example/generate_responses_in/input_file.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/example/generate_responses_in/input_file.jsonl -------------------------------------------------------------------------------- /scripts/synth_pref/example/generate_responses_out/model0/input_file.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/example/generate_responses_out/model0/input_file.jsonl -------------------------------------------------------------------------------- /scripts/synth_pref/example/generate_responses_out/model1/input_file.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/example/generate_responses_out/model1/input_file.jsonl -------------------------------------------------------------------------------- /scripts/synth_pref/example/generate_responses_out/model2/input_file.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/example/generate_responses_out/model2/input_file.jsonl -------------------------------------------------------------------------------- /scripts/synth_pref/example/generate_responses_out/model3/input_file.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/example/generate_responses_out/model3/input_file.jsonl -------------------------------------------------------------------------------- /scripts/synth_pref/generate_responses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/generate_responses.py -------------------------------------------------------------------------------- /scripts/synth_pref/parse_preferences.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/parse_preferences.py -------------------------------------------------------------------------------- /scripts/synth_pref/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/requirements.txt -------------------------------------------------------------------------------- /scripts/synth_pref/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/synth_pref/utils/model_configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/utils/model_configs.py -------------------------------------------------------------------------------- /scripts/synth_pref/utils/openai_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/utils/openai_api.py -------------------------------------------------------------------------------- /scripts/synth_pref/utils/ultrafeedback_template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synth_pref/utils/ultrafeedback_template.py -------------------------------------------------------------------------------- /scripts/synthetic_preference_dataset.bash: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/synthetic_preference_dataset.bash -------------------------------------------------------------------------------- /scripts/test_chat_templates.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/test_chat_templates.py -------------------------------------------------------------------------------- /scripts/train/benchmark.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/benchmark.sh -------------------------------------------------------------------------------- /scripts/train/build_image_and_launch.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/build_image_and_launch.sh -------------------------------------------------------------------------------- /scripts/train/build_image_and_launch_dirty.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/build_image_and_launch_dirty.sh -------------------------------------------------------------------------------- /scripts/train/debug/code.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/code.sh -------------------------------------------------------------------------------- /scripts/train/debug/cute_debug_system_prompt.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/cute_debug_system_prompt.txt -------------------------------------------------------------------------------- /scripts/train/debug/dpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/dpo.sh -------------------------------------------------------------------------------- /scripts/train/debug/finetune.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/finetune.sh -------------------------------------------------------------------------------- /scripts/train/debug/full_integration_test.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/full_integration_test.sh -------------------------------------------------------------------------------- /scripts/train/debug/grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/grpo.sh -------------------------------------------------------------------------------- /scripts/train/debug/grpo_fast.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/grpo_fast.sh -------------------------------------------------------------------------------- /scripts/train/debug/grpo_fast_3_gpu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/grpo_fast_3_gpu.sh -------------------------------------------------------------------------------- /scripts/train/debug/grpo_fast_llm_judge.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/grpo_fast_llm_judge.sh -------------------------------------------------------------------------------- /scripts/train/debug/grpo_fast_tool.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/grpo_fast_tool.sh -------------------------------------------------------------------------------- /scripts/train/debug/judge.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/judge.sh -------------------------------------------------------------------------------- /scripts/train/debug/large_test_script.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/large_test_script.sh -------------------------------------------------------------------------------- /scripts/train/debug/local_tool_grpo_fast.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/local_tool_grpo_fast.sh -------------------------------------------------------------------------------- /scripts/train/debug/ppo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/ppo.sh -------------------------------------------------------------------------------- /scripts/train/debug/ppo_fast.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/ppo_fast.sh -------------------------------------------------------------------------------- /scripts/train/debug/ppo_fast_2_gpu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/ppo_fast_2_gpu.sh -------------------------------------------------------------------------------- /scripts/train/debug/reward_modeling.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/reward_modeling.sh -------------------------------------------------------------------------------- /scripts/train/debug/single_gpu_integration_test.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/single_gpu_integration_test.sh -------------------------------------------------------------------------------- /scripts/train/debug/single_gpu_on_beaker.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/single_gpu_on_beaker.sh -------------------------------------------------------------------------------- /scripts/train/debug/tool_grpo_fast.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/debug/tool_grpo_fast.sh -------------------------------------------------------------------------------- /scripts/train/olmo2/dpo_13b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo2/dpo_13b.sh -------------------------------------------------------------------------------- /scripts/train/olmo2/dpo_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo2/dpo_7b.sh -------------------------------------------------------------------------------- /scripts/train/olmo2/finetune_13b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo2/finetune_13b.sh -------------------------------------------------------------------------------- /scripts/train/olmo2/finetune_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo2/finetune_32b.sh -------------------------------------------------------------------------------- /scripts/train/olmo2/finetune_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo2/finetune_7b.sh -------------------------------------------------------------------------------- /scripts/train/olmo2/grpo_13b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo2/grpo_13b.sh -------------------------------------------------------------------------------- /scripts/train/olmo2/grpo_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo2/grpo_7b.sh -------------------------------------------------------------------------------- /scripts/train/olmo2/grpo_fast_13b_zero.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo2/grpo_fast_13b_zero.sh -------------------------------------------------------------------------------- /scripts/train/olmo2/grpo_fast_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo2/grpo_fast_32b.sh -------------------------------------------------------------------------------- /scripts/train/olmo2/grpo_fast_32b_tulu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo2/grpo_fast_32b_tulu.sh -------------------------------------------------------------------------------- /scripts/train/olmo2/grpo_fast_7b_zero.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo2/grpo_fast_7b_zero.sh -------------------------------------------------------------------------------- /scripts/train/olmo3/32b_think_dpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo3/32b_think_dpo.sh -------------------------------------------------------------------------------- /scripts/train/olmo3/32b_think_rl.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo3/32b_think_rl.sh -------------------------------------------------------------------------------- /scripts/train/olmo3/7b_instruct_dpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo3/7b_instruct_dpo.sh -------------------------------------------------------------------------------- /scripts/train/olmo3/7b_instruct_rl.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo3/7b_instruct_rl.sh -------------------------------------------------------------------------------- /scripts/train/olmo3/7b_rlzero_code.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo3/7b_rlzero_code.sh -------------------------------------------------------------------------------- /scripts/train/olmo3/7b_rlzero_general.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo3/7b_rlzero_general.sh -------------------------------------------------------------------------------- /scripts/train/olmo3/7b_rlzero_instruction_following.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo3/7b_rlzero_instruction_following.sh -------------------------------------------------------------------------------- /scripts/train/olmo3/7b_rlzero_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo3/7b_rlzero_math.sh -------------------------------------------------------------------------------- /scripts/train/olmo3/7b_rlzero_mix.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo3/7b_rlzero_mix.sh -------------------------------------------------------------------------------- /scripts/train/olmo3/7b_think_dpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo3/7b_think_dpo.sh -------------------------------------------------------------------------------- /scripts/train/olmo3/7b_think_rl.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo3/7b_think_rl.sh -------------------------------------------------------------------------------- /scripts/train/olmo3/7b_think_rl_no_pipeline.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo3/7b_think_rl_no_pipeline.sh -------------------------------------------------------------------------------- /scripts/train/olmo3/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/olmo3/README.md -------------------------------------------------------------------------------- /scripts/train/qwen/finetune_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/qwen/finetune_7b.sh -------------------------------------------------------------------------------- /scripts/train/qwen/grpo_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/qwen/grpo_7b.sh -------------------------------------------------------------------------------- /scripts/train/qwen/grpo_fast_32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/qwen/grpo_fast_32b.sh -------------------------------------------------------------------------------- /scripts/train/qwen/grpo_fast_3b_single_node.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/qwen/grpo_fast_3b_single_node.sh -------------------------------------------------------------------------------- /scripts/train/qwen/grpo_fast_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/qwen/grpo_fast_7b.sh -------------------------------------------------------------------------------- /scripts/train/qwen/grpo_fast_7b_code.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/qwen/grpo_fast_7b_code.sh -------------------------------------------------------------------------------- /scripts/train/qwen/grpo_fast_7b_orz.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/qwen/grpo_fast_7b_orz.sh -------------------------------------------------------------------------------- /scripts/train/qwen/ppo_fast_7b_orz.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/qwen/ppo_fast_7b_orz.sh -------------------------------------------------------------------------------- /scripts/train/rlvr/grpo_fast_mini copy.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/rlvr/grpo_fast_mini copy.sh -------------------------------------------------------------------------------- /scripts/train/rlvr/grpo_fast_mini_old.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/rlvr/grpo_fast_mini_old.sh -------------------------------------------------------------------------------- /scripts/train/rlvr/grpo_llama3.1-8b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/rlvr/grpo_llama3.1-8b.sh -------------------------------------------------------------------------------- /scripts/train/rlvr/grpo_mini_base.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/rlvr/grpo_mini_base.sh -------------------------------------------------------------------------------- /scripts/train/rlvr/grpo_mini_base_fast.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/rlvr/grpo_mini_base_fast.sh -------------------------------------------------------------------------------- /scripts/train/rlvr/grpo_mini_base_fast1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/rlvr/grpo_mini_base_fast1.sh -------------------------------------------------------------------------------- /scripts/train/rlvr/grpo_mini_base_fast1_test_oom.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/rlvr/grpo_mini_base_fast1_test_oom.sh -------------------------------------------------------------------------------- /scripts/train/rlvr/grpo_qwen_fast_2.5_7B_best.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/rlvr/grpo_qwen_fast_2.5_7B_best.sh -------------------------------------------------------------------------------- /scripts/train/rlvr/judge_general_verifier.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/rlvr/judge_general_verifier.sh -------------------------------------------------------------------------------- /scripts/train/rlvr/tulu_rlvr.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/rlvr/tulu_rlvr.sh -------------------------------------------------------------------------------- /scripts/train/rlvr/valpy_if.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/rlvr/valpy_if.sh -------------------------------------------------------------------------------- /scripts/train/rlvr/valpy_if_grpo_fast.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/rlvr/valpy_if_grpo_fast.sh -------------------------------------------------------------------------------- /scripts/train/tulu3/dpo_8b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/tulu3/dpo_8b.sh -------------------------------------------------------------------------------- /scripts/train/tulu3/finetune_8b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/tulu3/finetune_8b.sh -------------------------------------------------------------------------------- /scripts/train/tulu3/grpo_8b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/tulu3/grpo_8b.sh -------------------------------------------------------------------------------- /scripts/train/tulu3/grpo_fast_8b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/tulu3/grpo_fast_8b.sh -------------------------------------------------------------------------------- /scripts/train/tulu3/grpo_fast_8b_code_dpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/tulu3/grpo_fast_8b_code_dpo.sh -------------------------------------------------------------------------------- /scripts/train/tulu3/grpo_fast_8b_code_sft.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/tulu3/grpo_fast_8b_code_sft.sh -------------------------------------------------------------------------------- /scripts/train/tulu3/grpo_fast_8b_single_node.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/tulu3/grpo_fast_8b_single_node.sh -------------------------------------------------------------------------------- /scripts/train/tulu3/ppo_8b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/tulu3/ppo_8b.sh -------------------------------------------------------------------------------- /scripts/train/tulu3/reward_modeling_8b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/train/tulu3/reward_modeling_8b.sh -------------------------------------------------------------------------------- /scripts/wait_beaker_dataset_model_upload_then_evaluate_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/wait_beaker_dataset_model_upload_then_evaluate_model.py -------------------------------------------------------------------------------- /scripts/weights/convert_llama_weights_to_hf.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/weights/convert_llama_weights_to_hf.sh -------------------------------------------------------------------------------- /scripts/weights/weight_diff.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/scripts/weights/weight_diff.py -------------------------------------------------------------------------------- /test_mason.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/test_mason.py -------------------------------------------------------------------------------- /uv.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/open-instruct/HEAD/uv.lock --------------------------------------------------------------------------------