├── .DS_Store ├── README.md ├── lab1 ├── requirements.txt └── tryllm.ipynb ├── lab10 ├── 00_train_with_preference_AI_safety.ipynb ├── Llama3-8B-Instruct-dpo.yaml ├── Lora_Merge.yaml ├── download.py ├── readme.md └── requirements.txt ├── lab2 └── prompts.ipynb ├── lab3 ├── langchain.ipynb └── requirements.txt ├── lab4 ├── memory.ipynb └── requirements.txt ├── lab5 ├── 0-checking_gpus.ipynb ├── 1-lab5.ipynb ├── 2-text_to_image.ipynb ├── assets │ ├── detail.png │ ├── manual.png │ ├── port.png │ ├── preview.png │ ├── sd-base.png │ ├── sd-ckpt.png │ ├── sd-create-emb.png │ ├── sd-hdst.jpeg │ ├── sd-port.png │ ├── sd-preprocess.png │ ├── sd-result.png │ ├── sd-sample.png │ ├── sd-train.png │ ├── select.png │ ├── teaser.JPG │ └── training.JPG ├── comfy_example_workflows │ ├── boricuapab_svd_racecar_comfyworkflows.json │ ├── sd3_medium_example_workflow_basic.json │ └── sd3_medium_example_workflow_multi_prompt.json └── sam2 │ └── configs │ ├── sam2.1 │ ├── sam2.1_hiera_b+.yaml │ ├── sam2.1_hiera_l.yaml │ ├── sam2.1_hiera_s.yaml │ └── sam2.1_hiera_t.yaml │ ├── sam2.1_training │ └── sam2.1_hiera_b+_MOSE_finetune.yaml │ └── sam2 │ ├── sam2_hiera_b+.yaml │ ├── sam2_hiera_l.yaml │ ├── sam2_hiera_s.yaml │ └── sam2_hiera_t.yaml ├── lab6 ├── 01_evaluation.ipynb ├── 02_Phi-3.ipynb ├── 03_llm-as-judge.ipynb └── requirements.txt ├── lab7 ├── assets │ └── request.jpg ├── lab7.ipynb ├── llm-optimization.ipynb └── parallelism.ipynb ├── lab8 ├── 01_llama_factory.ipynb ├── 02_poet_data.ipynb ├── Llama3-8B-Instruct-sft.yaml ├── Lora_Merge.yaml └── requirements.txt └── lab9 ├── Logic-RL ├── .gitignore ├── LICENSE ├── Notice.txt ├── README.md ├── data │ └── kk │ │ └── instruct │ │ ├── 3ppl │ │ ├── test.parquet │ │ └── train.parquet │ │ ├── 4ppl │ │ ├── test.parquet │ │ └── train.parquet │ │ ├── 5ppl │ │ ├── test.parquet │ │ └── train.parquet │ │ ├── 6ppl │ │ ├── test.parquet │ │ └── train.parquet │ │ └── 7ppl │ │ ├── test.parquet │ │ └── train.parquet ├── docker │ ├── Dockerfile.ngc.vllm │ └── Dockerfile.vemlp.vllm.te ├── docs │ ├── Makefile │ ├── README.md │ ├── _static │ │ └── logo.png │ ├── advance │ │ ├── dpo_extension.rst │ │ ├── fsdp_extension.rst │ │ ├── megatron_extension.rst │ │ └── placement.rst │ ├── conf.py │ ├── examples │ │ ├── config.rst │ │ ├── gsm8k_example.rst │ │ └── ppo_code_architecture.rst │ ├── experiment │ │ └── ppo.rst │ ├── faq │ │ └── faq.rst │ ├── index.rst │ ├── preparation │ │ ├── prepare_data.rst │ │ └── reward_function.rst │ ├── requirements-docs.txt │ ├── start │ │ ├── install.rst │ │ └── quickstart.rst │ └── workers │ │ ├── fsdp_workers.rst │ │ ├── megatron_workers.rst │ │ └── ray_trainer.rst ├── eval_kk │ ├── compute_score.py │ ├── eval.sh │ ├── kk_processor.py │ ├── kk_prompt.py │ └── main_eval_instruct.py ├── examples │ ├── data_preprocess │ │ ├── arth.py │ │ ├── countdown.py │ │ ├── full_hh_rlhf.py │ │ ├── gsm8k.py │ │ ├── hellaswag.py │ │ ├── kk.py │ │ ├── math_dataset.py │ │ └── multiply.py │ ├── generation │ │ └── run_deepseek_v2_lite_math.sh │ ├── grpo_trainer │ │ ├── run_deepseek7b_llm.sh │ │ ├── run_deepseek7b_llm_seq_balance.sh │ │ ├── run_qwen2-7b.sh │ │ └── run_qwen2-7b_seq_balance.sh │ ├── ppo_trainer │ │ ├── run_deepseek7b_llm.sh │ │ ├── run_deepseek7b_llm_sp2.sh │ │ ├── run_deepseek_full_hh_rlhf.sh │ │ ├── run_deepseek_math_gsm8k_megatron.sh │ │ ├── run_deepseek_megatron.sh │ │ ├── run_gemma.sh │ │ ├── run_qwen2-7b.sh │ │ ├── run_qwen2-7b_rm.sh │ │ ├── run_qwen2-7b_rm_seq_balance.sh │ │ ├── run_qwen2-7b_seq_balance.sh │ │ ├── run_qwen2.5-32b.sh │ │ └── verl_getting_started.ipynb │ ├── ray │ │ └── tutorial.ipynb │ ├── sft │ │ └── gsm8k │ │ │ ├── run_deepseek_6b7.sh │ │ │ ├── run_gemma_2b.sh │ │ │ └── run_gemma_7b.sh │ └── split_placement │ │ ├── README.md │ │ ├── config │ │ └── ppo_trainer_split.yaml │ │ ├── main_ppo_split.py │ │ ├── run_deepseek7b_llm.sh │ │ └── split_monkey_patch.py ├── main_grpo.sh ├── patches │ └── megatron_v4.patch ├── pics │ ├── response.png │ ├── response_mean_length.png │ ├── response_mean_length_v2.png │ ├── teaser.png │ └── test_score_plot_v1.jpg ├── pyproject.toml ├── requirements.txt ├── scripts │ ├── curriculum.sh │ ├── format.sh │ ├── train_grpo_4gpu_7Binstruct.sh │ ├── train_ppo_3B_4gpu.sh │ ├── train_ppo_7B_4gpu.sh │ └── train_reinforce_plus_4gpu_7Binstruct.sh ├── setup.py ├── setup.sh ├── test.py ├── tests │ ├── e2e │ │ ├── arithmetic_sequence │ │ │ ├── data │ │ │ │ ├── create_dataset.py │ │ │ │ ├── test.parquet │ │ │ │ └── train.parquet │ │ │ ├── model │ │ │ │ ├── config.json │ │ │ │ ├── create_model_tokenizer.py │ │ │ │ ├── generation_config.json │ │ │ │ ├── model.safetensors │ │ │ │ └── tokenizer_config.json │ │ │ └── rl │ │ │ │ ├── README.md │ │ │ │ ├── config │ │ │ │ └── ray_trainer.yaml │ │ │ │ └── main_trainer.py │ │ ├── run_qwen_gsm8k_model_rm.sh │ │ └── run_ray_trainer_rmpad.sh │ └── rollout │ │ ├── run_fsdp_vllm.py │ │ └── test_vllm_hf_loader.py └── verl │ ├── __init__.py │ ├── models │ ├── README.md │ ├── __init__.py │ ├── llama │ │ ├── __init__.py │ │ └── megatron │ │ │ ├── __init__.py │ │ │ ├── checkpoint_utils │ │ │ ├── __init__.py │ │ │ ├── llama_loader.py │ │ │ └── llama_saver.py │ │ │ ├── layers │ │ │ ├── __init__.py │ │ │ ├── parallel_attention.py │ │ │ ├── parallel_decoder.py │ │ │ ├── parallel_linear.py │ │ │ ├── parallel_mlp.py │ │ │ └── parallel_rmsnorm.py │ │ │ └── modeling_llama_megatron.py │ ├── registry.py │ ├── transformers │ │ ├── __init__.py │ │ ├── llama.py │ │ ├── monkey_patch.py │ │ └── qwen2.py │ └── weight_loader_registry.py │ ├── protocol.py │ ├── single_controller │ ├── __init__.py │ ├── base │ │ ├── __init__.py │ │ ├── decorator.py │ │ ├── megatron │ │ │ ├── __init__.py │ │ │ ├── worker.py │ │ │ └── worker_group.py │ │ ├── register_center │ │ │ ├── __init__.py │ │ │ └── ray.py │ │ ├── worker.py │ │ └── worker_group.py │ ├── ray │ │ ├── __init__.py │ │ ├── base.py │ │ └── megatron.py │ └── version │ │ └── version │ ├── third_party │ ├── __init__.py │ └── vllm │ │ ├── __init__.py │ │ ├── vllm_v_0_3_1 │ │ ├── __init__.py │ │ ├── arg_utils.py │ │ ├── config.py │ │ ├── llm.py │ │ ├── llm_engine_sp.py │ │ ├── model_loader.py │ │ ├── model_runner.py │ │ ├── parallel_state.py │ │ ├── tokenizer.py │ │ ├── weight_loaders.py │ │ └── worker.py │ │ ├── vllm_v_0_4_2 │ │ ├── __init__.py │ │ ├── arg_utils.py │ │ ├── config.py │ │ ├── dtensor_weight_loaders.py │ │ ├── hf_weight_loader.py │ │ ├── llm.py │ │ ├── llm_engine_sp.py │ │ ├── megatron_weight_loaders.py │ │ ├── model_loader.py │ │ ├── model_runner.py │ │ ├── parallel_state.py │ │ ├── spmd_gpu_executor.py │ │ ├── tokenizer.py │ │ └── worker.py │ │ ├── vllm_v_0_5_4 │ │ ├── __init__.py │ │ ├── arg_utils.py │ │ ├── config.py │ │ ├── dtensor_weight_loaders.py │ │ ├── hf_weight_loader.py │ │ ├── llm.py │ │ ├── llm_engine_sp.py │ │ ├── megatron_weight_loaders.py │ │ ├── model_loader.py │ │ ├── model_runner.py │ │ ├── parallel_state.py │ │ ├── spmd_gpu_executor.py │ │ ├── tokenizer.py │ │ └── worker.py │ │ └── vllm_v_0_6_3 │ │ ├── __init__.py │ │ ├── arg_utils.py │ │ ├── config.py │ │ ├── dtensor_weight_loaders.py │ │ ├── hf_weight_loader.py │ │ ├── llm.py │ │ ├── llm_engine_sp.py │ │ ├── megatron_weight_loaders.py │ │ ├── model_loader.py │ │ ├── model_runner.py │ │ ├── parallel_state.py │ │ ├── spmd_gpu_executor.py │ │ ├── tokenizer.py │ │ └── worker.py │ ├── trainer │ ├── __init__.py │ ├── config │ │ ├── evaluation.yaml │ │ ├── generation.yaml │ │ ├── ppo_megatron_trainer.yaml │ │ ├── ppo_trainer.yaml │ │ └── sft_trainer.yaml │ ├── fsdp_sft_trainer.py │ ├── main_eval.py │ ├── main_generation.py │ ├── main_ppo.py │ ├── ppo │ │ ├── __init__.py │ │ ├── core_algos.py │ │ └── ray_trainer.py │ └── runtime_env.yaml │ ├── utils │ ├── __init__.py │ ├── config.py │ ├── dataset │ │ ├── README.md │ │ ├── __init__.py │ │ ├── rl_dataset.py │ │ ├── rm_dataset.py │ │ └── sft_dataset.py │ ├── debug │ │ ├── __init__.py │ │ ├── performance.py │ │ └── trajectory_tracker.py │ ├── distributed.py │ ├── flops_counter.py │ ├── fs.py │ ├── fsdp_utils.py │ ├── hdfs_io.py │ ├── import_utils.py │ ├── logger │ │ ├── __init__.py │ │ └── aggregate_logger.py │ ├── logging_utils.py │ ├── megatron │ │ ├── __init__.py │ │ ├── memory.py │ │ ├── optimizer.py │ │ ├── optimizer_config.py │ │ ├── pipeline_parallel.py │ │ ├── sequence_parallel.py │ │ └── tensor_parallel.py │ ├── megatron_utils.py │ ├── memory_buffer.py │ ├── model.py │ ├── py_functional.py │ ├── ray_utils.py │ ├── rendezvous │ │ ├── __init__.py │ │ └── ray_backend.py │ ├── reward_score │ │ ├── __init__.py │ │ ├── countdown.py │ │ ├── gsm8k.py │ │ ├── kk.py │ │ ├── math.py │ │ └── multiply.py │ ├── seqlen_balancing.py │ ├── tokenizer.py │ ├── torch_dtypes.py │ ├── torch_functional.py │ ├── tracking.py │ └── ulysses.py │ ├── version │ └── version │ └── workers │ ├── __init__.py │ ├── actor │ ├── __init__.py │ ├── base.py │ ├── dp_actor.py │ └── megatron_actor.py │ ├── critic │ ├── __init__.py │ ├── base.py │ ├── dp_critic.py │ └── megatron_critic.py │ ├── fsdp_workers.py │ ├── megatron_workers.py │ ├── reward_model │ ├── __init__.py │ ├── base.py │ └── megatron │ │ ├── __init__.py │ │ └── reward_model.py │ ├── rollout │ ├── __init__.py │ ├── base.py │ ├── hf_rollout.py │ ├── naive │ │ ├── __init__.py │ │ └── naive_rollout.py │ ├── tokenizer.py │ └── vllm_rollout │ │ ├── __init__.py │ │ └── vllm_rollout.py │ └── sharding_manager │ ├── __init__.py │ ├── base.py │ ├── fsdp_ulysses.py │ ├── fsdp_vllm.py │ └── megatron_vllm.py └── task.ipynb /.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/.DS_Store -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/README.md -------------------------------------------------------------------------------- /lab1/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab1/requirements.txt -------------------------------------------------------------------------------- /lab1/tryllm.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab1/tryllm.ipynb -------------------------------------------------------------------------------- /lab10/00_train_with_preference_AI_safety.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab10/00_train_with_preference_AI_safety.ipynb -------------------------------------------------------------------------------- /lab10/Llama3-8B-Instruct-dpo.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab10/Llama3-8B-Instruct-dpo.yaml -------------------------------------------------------------------------------- /lab10/Lora_Merge.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab10/Lora_Merge.yaml -------------------------------------------------------------------------------- /lab10/download.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab10/download.py -------------------------------------------------------------------------------- /lab10/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab10/readme.md -------------------------------------------------------------------------------- /lab10/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab10/requirements.txt -------------------------------------------------------------------------------- /lab2/prompts.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab2/prompts.ipynb -------------------------------------------------------------------------------- /lab3/langchain.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab3/langchain.ipynb -------------------------------------------------------------------------------- /lab3/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab3/requirements.txt -------------------------------------------------------------------------------- /lab4/memory.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab4/memory.ipynb -------------------------------------------------------------------------------- /lab4/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab4/requirements.txt -------------------------------------------------------------------------------- /lab5/0-checking_gpus.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/0-checking_gpus.ipynb -------------------------------------------------------------------------------- /lab5/1-lab5.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/1-lab5.ipynb -------------------------------------------------------------------------------- /lab5/2-text_to_image.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/2-text_to_image.ipynb -------------------------------------------------------------------------------- /lab5/assets/detail.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/detail.png -------------------------------------------------------------------------------- /lab5/assets/manual.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/manual.png -------------------------------------------------------------------------------- /lab5/assets/port.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/port.png -------------------------------------------------------------------------------- /lab5/assets/preview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/preview.png -------------------------------------------------------------------------------- /lab5/assets/sd-base.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/sd-base.png -------------------------------------------------------------------------------- /lab5/assets/sd-ckpt.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/sd-ckpt.png -------------------------------------------------------------------------------- /lab5/assets/sd-create-emb.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/sd-create-emb.png -------------------------------------------------------------------------------- /lab5/assets/sd-hdst.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/sd-hdst.jpeg -------------------------------------------------------------------------------- /lab5/assets/sd-port.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/sd-port.png -------------------------------------------------------------------------------- /lab5/assets/sd-preprocess.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/sd-preprocess.png -------------------------------------------------------------------------------- /lab5/assets/sd-result.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/sd-result.png -------------------------------------------------------------------------------- /lab5/assets/sd-sample.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/sd-sample.png -------------------------------------------------------------------------------- /lab5/assets/sd-train.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/sd-train.png -------------------------------------------------------------------------------- /lab5/assets/select.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/select.png -------------------------------------------------------------------------------- /lab5/assets/teaser.JPG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/teaser.JPG -------------------------------------------------------------------------------- /lab5/assets/training.JPG: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/assets/training.JPG -------------------------------------------------------------------------------- /lab5/comfy_example_workflows/boricuapab_svd_racecar_comfyworkflows.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/comfy_example_workflows/boricuapab_svd_racecar_comfyworkflows.json -------------------------------------------------------------------------------- /lab5/comfy_example_workflows/sd3_medium_example_workflow_basic.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/comfy_example_workflows/sd3_medium_example_workflow_basic.json -------------------------------------------------------------------------------- /lab5/comfy_example_workflows/sd3_medium_example_workflow_multi_prompt.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/comfy_example_workflows/sd3_medium_example_workflow_multi_prompt.json -------------------------------------------------------------------------------- /lab5/sam2/configs/sam2.1/sam2.1_hiera_b+.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/sam2/configs/sam2.1/sam2.1_hiera_b+.yaml -------------------------------------------------------------------------------- /lab5/sam2/configs/sam2.1/sam2.1_hiera_l.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/sam2/configs/sam2.1/sam2.1_hiera_l.yaml -------------------------------------------------------------------------------- /lab5/sam2/configs/sam2.1/sam2.1_hiera_s.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/sam2/configs/sam2.1/sam2.1_hiera_s.yaml -------------------------------------------------------------------------------- /lab5/sam2/configs/sam2.1/sam2.1_hiera_t.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/sam2/configs/sam2.1/sam2.1_hiera_t.yaml -------------------------------------------------------------------------------- /lab5/sam2/configs/sam2.1_training/sam2.1_hiera_b+_MOSE_finetune.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/sam2/configs/sam2.1_training/sam2.1_hiera_b+_MOSE_finetune.yaml -------------------------------------------------------------------------------- /lab5/sam2/configs/sam2/sam2_hiera_b+.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/sam2/configs/sam2/sam2_hiera_b+.yaml -------------------------------------------------------------------------------- /lab5/sam2/configs/sam2/sam2_hiera_l.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/sam2/configs/sam2/sam2_hiera_l.yaml -------------------------------------------------------------------------------- /lab5/sam2/configs/sam2/sam2_hiera_s.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/sam2/configs/sam2/sam2_hiera_s.yaml -------------------------------------------------------------------------------- /lab5/sam2/configs/sam2/sam2_hiera_t.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab5/sam2/configs/sam2/sam2_hiera_t.yaml -------------------------------------------------------------------------------- /lab6/01_evaluation.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab6/01_evaluation.ipynb -------------------------------------------------------------------------------- /lab6/02_Phi-3.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab6/02_Phi-3.ipynb -------------------------------------------------------------------------------- /lab6/03_llm-as-judge.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab6/03_llm-as-judge.ipynb -------------------------------------------------------------------------------- /lab6/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab6/requirements.txt -------------------------------------------------------------------------------- /lab7/assets/request.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab7/assets/request.jpg -------------------------------------------------------------------------------- /lab7/lab7.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab7/lab7.ipynb -------------------------------------------------------------------------------- /lab7/llm-optimization.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab7/llm-optimization.ipynb -------------------------------------------------------------------------------- /lab7/parallelism.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab7/parallelism.ipynb -------------------------------------------------------------------------------- /lab8/01_llama_factory.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab8/01_llama_factory.ipynb -------------------------------------------------------------------------------- /lab8/02_poet_data.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab8/02_poet_data.ipynb -------------------------------------------------------------------------------- /lab8/Llama3-8B-Instruct-sft.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab8/Llama3-8B-Instruct-sft.yaml -------------------------------------------------------------------------------- /lab8/Lora_Merge.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab8/Lora_Merge.yaml -------------------------------------------------------------------------------- /lab8/requirements.txt: -------------------------------------------------------------------------------- 1 | trl 2 | fire 3 | bitsandbytes 4 | deepspeed -------------------------------------------------------------------------------- /lab9/Logic-RL/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/.gitignore -------------------------------------------------------------------------------- /lab9/Logic-RL/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/LICENSE -------------------------------------------------------------------------------- /lab9/Logic-RL/Notice.txt: -------------------------------------------------------------------------------- 1 | Copyright 2023-2024 Bytedance Ltd. and/or its affiliates -------------------------------------------------------------------------------- /lab9/Logic-RL/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/README.md -------------------------------------------------------------------------------- /lab9/Logic-RL/data/kk/instruct/3ppl/test.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/data/kk/instruct/3ppl/test.parquet -------------------------------------------------------------------------------- /lab9/Logic-RL/data/kk/instruct/3ppl/train.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/data/kk/instruct/3ppl/train.parquet -------------------------------------------------------------------------------- /lab9/Logic-RL/data/kk/instruct/4ppl/test.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/data/kk/instruct/4ppl/test.parquet -------------------------------------------------------------------------------- /lab9/Logic-RL/data/kk/instruct/4ppl/train.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/data/kk/instruct/4ppl/train.parquet -------------------------------------------------------------------------------- /lab9/Logic-RL/data/kk/instruct/5ppl/test.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/data/kk/instruct/5ppl/test.parquet -------------------------------------------------------------------------------- /lab9/Logic-RL/data/kk/instruct/5ppl/train.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/data/kk/instruct/5ppl/train.parquet -------------------------------------------------------------------------------- /lab9/Logic-RL/data/kk/instruct/6ppl/test.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/data/kk/instruct/6ppl/test.parquet -------------------------------------------------------------------------------- /lab9/Logic-RL/data/kk/instruct/6ppl/train.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/data/kk/instruct/6ppl/train.parquet -------------------------------------------------------------------------------- /lab9/Logic-RL/data/kk/instruct/7ppl/test.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/data/kk/instruct/7ppl/test.parquet -------------------------------------------------------------------------------- /lab9/Logic-RL/data/kk/instruct/7ppl/train.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/data/kk/instruct/7ppl/train.parquet -------------------------------------------------------------------------------- /lab9/Logic-RL/docker/Dockerfile.ngc.vllm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docker/Dockerfile.ngc.vllm -------------------------------------------------------------------------------- /lab9/Logic-RL/docker/Dockerfile.vemlp.vllm.te: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docker/Dockerfile.vemlp.vllm.te -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/Makefile -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/README.md -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/_static/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/_static/logo.png -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/advance/dpo_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/advance/dpo_extension.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/advance/fsdp_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/advance/fsdp_extension.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/advance/megatron_extension.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/advance/megatron_extension.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/advance/placement.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/advance/placement.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/conf.py -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/examples/config.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/examples/config.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/examples/gsm8k_example.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/examples/gsm8k_example.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/examples/ppo_code_architecture.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/examples/ppo_code_architecture.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/experiment/ppo.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/experiment/ppo.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/faq/faq.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/faq/faq.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/index.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/preparation/prepare_data.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/preparation/prepare_data.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/preparation/reward_function.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/preparation/reward_function.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/requirements-docs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/requirements-docs.txt -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/start/install.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/start/install.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/start/quickstart.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/start/quickstart.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/workers/fsdp_workers.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/workers/fsdp_workers.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/workers/megatron_workers.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/workers/megatron_workers.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/docs/workers/ray_trainer.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/docs/workers/ray_trainer.rst -------------------------------------------------------------------------------- /lab9/Logic-RL/eval_kk/compute_score.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/eval_kk/compute_score.py -------------------------------------------------------------------------------- /lab9/Logic-RL/eval_kk/eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/eval_kk/eval.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/eval_kk/kk_processor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/eval_kk/kk_processor.py -------------------------------------------------------------------------------- /lab9/Logic-RL/eval_kk/kk_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/eval_kk/kk_prompt.py -------------------------------------------------------------------------------- /lab9/Logic-RL/eval_kk/main_eval_instruct.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/eval_kk/main_eval_instruct.py -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/data_preprocess/arth.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/data_preprocess/arth.py -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/data_preprocess/countdown.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/data_preprocess/countdown.py -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/data_preprocess/full_hh_rlhf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/data_preprocess/full_hh_rlhf.py -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/data_preprocess/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/data_preprocess/gsm8k.py -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/data_preprocess/hellaswag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/data_preprocess/hellaswag.py -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/data_preprocess/kk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/data_preprocess/kk.py -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/data_preprocess/math_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/data_preprocess/math_dataset.py -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/data_preprocess/multiply.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/data_preprocess/multiply.py -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/generation/run_deepseek_v2_lite_math.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/generation/run_deepseek_v2_lite_math.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/grpo_trainer/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/grpo_trainer/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/grpo_trainer/run_deepseek7b_llm_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/grpo_trainer/run_deepseek7b_llm_seq_balance.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/grpo_trainer/run_qwen2-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/grpo_trainer/run_qwen2-7b.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/grpo_trainer/run_qwen2-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/grpo_trainer/run_qwen2-7b_seq_balance.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/ppo_trainer/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/ppo_trainer/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/ppo_trainer/run_deepseek7b_llm_sp2.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/ppo_trainer/run_deepseek7b_llm_sp2.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/ppo_trainer/run_deepseek_full_hh_rlhf.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/ppo_trainer/run_deepseek_full_hh_rlhf.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/ppo_trainer/run_deepseek_math_gsm8k_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/ppo_trainer/run_deepseek_math_gsm8k_megatron.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/ppo_trainer/run_deepseek_megatron.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/ppo_trainer/run_deepseek_megatron.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/ppo_trainer/run_gemma.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/ppo_trainer/run_gemma.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/ppo_trainer/run_qwen2-7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/ppo_trainer/run_qwen2-7b.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/ppo_trainer/run_qwen2-7b_rm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/ppo_trainer/run_qwen2-7b_rm.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/ppo_trainer/run_qwen2-7b_rm_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/ppo_trainer/run_qwen2-7b_rm_seq_balance.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/ppo_trainer/run_qwen2-7b_seq_balance.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/ppo_trainer/run_qwen2-7b_seq_balance.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/ppo_trainer/run_qwen2.5-32b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/ppo_trainer/run_qwen2.5-32b.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/ppo_trainer/verl_getting_started.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/ppo_trainer/verl_getting_started.ipynb -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/ray/tutorial.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/ray/tutorial.ipynb -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/sft/gsm8k/run_deepseek_6b7.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/sft/gsm8k/run_deepseek_6b7.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/sft/gsm8k/run_gemma_2b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/sft/gsm8k/run_gemma_2b.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/sft/gsm8k/run_gemma_7b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/sft/gsm8k/run_gemma_7b.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/split_placement/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/split_placement/README.md -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/split_placement/config/ppo_trainer_split.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/split_placement/config/ppo_trainer_split.yaml -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/split_placement/main_ppo_split.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/split_placement/main_ppo_split.py -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/split_placement/run_deepseek7b_llm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/split_placement/run_deepseek7b_llm.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/examples/split_placement/split_monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/examples/split_placement/split_monkey_patch.py -------------------------------------------------------------------------------- /lab9/Logic-RL/main_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/main_grpo.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/patches/megatron_v4.patch: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/patches/megatron_v4.patch -------------------------------------------------------------------------------- /lab9/Logic-RL/pics/response.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/pics/response.png -------------------------------------------------------------------------------- /lab9/Logic-RL/pics/response_mean_length.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/pics/response_mean_length.png -------------------------------------------------------------------------------- /lab9/Logic-RL/pics/response_mean_length_v2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/pics/response_mean_length_v2.png -------------------------------------------------------------------------------- /lab9/Logic-RL/pics/teaser.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/pics/teaser.png -------------------------------------------------------------------------------- /lab9/Logic-RL/pics/test_score_plot_v1.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/pics/test_score_plot_v1.jpg -------------------------------------------------------------------------------- /lab9/Logic-RL/pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/pyproject.toml -------------------------------------------------------------------------------- /lab9/Logic-RL/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/requirements.txt -------------------------------------------------------------------------------- /lab9/Logic-RL/scripts/curriculum.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/scripts/curriculum.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/scripts/format.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/scripts/format.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/scripts/train_grpo_4gpu_7Binstruct.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/scripts/train_grpo_4gpu_7Binstruct.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/scripts/train_ppo_3B_4gpu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/scripts/train_ppo_3B_4gpu.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/scripts/train_ppo_7B_4gpu.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/scripts/train_ppo_7B_4gpu.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/scripts/train_reinforce_plus_4gpu_7Binstruct.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/scripts/train_reinforce_plus_4gpu_7Binstruct.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/setup.py -------------------------------------------------------------------------------- /lab9/Logic-RL/setup.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/setup.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/test.py -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/e2e/arithmetic_sequence/data/create_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/e2e/arithmetic_sequence/data/create_dataset.py -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/e2e/arithmetic_sequence/data/test.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/e2e/arithmetic_sequence/data/test.parquet -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/e2e/arithmetic_sequence/data/train.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/e2e/arithmetic_sequence/data/train.parquet -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/e2e/arithmetic_sequence/model/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/e2e/arithmetic_sequence/model/config.json -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/e2e/arithmetic_sequence/model/create_model_tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/e2e/arithmetic_sequence/model/create_model_tokenizer.py -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/e2e/arithmetic_sequence/model/generation_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/e2e/arithmetic_sequence/model/generation_config.json -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/e2e/arithmetic_sequence/model/model.safetensors: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/e2e/arithmetic_sequence/model/model.safetensors -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/e2e/arithmetic_sequence/model/tokenizer_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/e2e/arithmetic_sequence/model/tokenizer_config.json -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/e2e/arithmetic_sequence/rl/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/e2e/arithmetic_sequence/rl/README.md -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/e2e/arithmetic_sequence/rl/config/ray_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/e2e/arithmetic_sequence/rl/config/ray_trainer.yaml -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/e2e/arithmetic_sequence/rl/main_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/e2e/arithmetic_sequence/rl/main_trainer.py -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/e2e/run_qwen_gsm8k_model_rm.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/e2e/run_qwen_gsm8k_model_rm.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/e2e/run_ray_trainer_rmpad.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/e2e/run_ray_trainer_rmpad.sh -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/rollout/run_fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/rollout/run_fsdp_vllm.py -------------------------------------------------------------------------------- /lab9/Logic-RL/tests/rollout/test_vllm_hf_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/tests/rollout/test_vllm_hf_loader.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/README.md -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/llama/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/llama/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/llama/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/llama/megatron/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/llama/megatron/checkpoint_utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/llama/megatron/checkpoint_utils/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/llama/megatron/checkpoint_utils/llama_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/llama/megatron/checkpoint_utils/llama_loader.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/llama/megatron/checkpoint_utils/llama_saver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/llama/megatron/checkpoint_utils/llama_saver.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/llama/megatron/layers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/llama/megatron/layers/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/llama/megatron/layers/parallel_attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/llama/megatron/layers/parallel_attention.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/llama/megatron/layers/parallel_decoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/llama/megatron/layers/parallel_decoder.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/llama/megatron/layers/parallel_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/llama/megatron/layers/parallel_linear.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/llama/megatron/layers/parallel_mlp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/llama/megatron/layers/parallel_mlp.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/llama/megatron/layers/parallel_rmsnorm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/llama/megatron/layers/parallel_rmsnorm.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/llama/megatron/modeling_llama_megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/llama/megatron/modeling_llama_megatron.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/registry.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/transformers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/transformers/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/transformers/llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/transformers/llama.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/transformers/monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/transformers/monkey_patch.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/transformers/qwen2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/transformers/qwen2.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/models/weight_loader_registry.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/models/weight_loader_registry.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/protocol.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/single_controller/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/base/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/single_controller/base/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/base/decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/single_controller/base/decorator.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/base/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/single_controller/base/megatron/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/base/megatron/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/single_controller/base/megatron/worker.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/base/megatron/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/single_controller/base/megatron/worker_group.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/base/register_center/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/single_controller/base/register_center/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/base/register_center/ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/single_controller/base/register_center/ray.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/base/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/single_controller/base/worker.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/base/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/single_controller/base/worker_group.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/ray/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/single_controller/ray/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/ray/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/single_controller/ray/base.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/ray/megatron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/single_controller/ray/megatron.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/single_controller/version/version: -------------------------------------------------------------------------------- 1 | 0.0.2 -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/arg_utils.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/config.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/llm.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/llm_engine_sp.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/model_loader.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/model_runner.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/parallel_state.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/tokenizer.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/weight_loaders.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_3_1/worker.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/arg_utils.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/config.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/dtensor_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/dtensor_weight_loaders.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/hf_weight_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/hf_weight_loader.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/llm.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/llm_engine_sp.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/megatron_weight_loaders.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/model_loader.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/model_runner.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/parallel_state.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/spmd_gpu_executor.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/tokenizer.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_4_2/worker.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/arg_utils.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/config.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/dtensor_weight_loaders.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/hf_weight_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/hf_weight_loader.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/llm.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/llm_engine_sp.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/megatron_weight_loaders.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/model_loader.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/model_runner.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/parallel_state.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/spmd_gpu_executor.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/tokenizer.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_5_4/worker.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/arg_utils.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/config.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/dtensor_weight_loaders.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/hf_weight_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/hf_weight_loader.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/llm.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/llm_engine_sp.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/megatron_weight_loaders.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/model_loader.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/model_runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/model_runner.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/parallel_state.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/spmd_gpu_executor.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/tokenizer.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/third_party/vllm/vllm_v_0_6_3/worker.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/config/evaluation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/config/evaluation.yaml -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/config/generation.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/config/generation.yaml -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/config/ppo_megatron_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/config/ppo_megatron_trainer.yaml -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/config/ppo_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/config/ppo_trainer.yaml -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/config/sft_trainer.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/config/sft_trainer.yaml -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/fsdp_sft_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/fsdp_sft_trainer.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/main_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/main_eval.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/main_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/main_generation.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/main_ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/main_ppo.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/ppo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/ppo/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/ppo/core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/ppo/core_algos.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/ppo/ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/ppo/ray_trainer.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/trainer/runtime_env.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/trainer/runtime_env.yaml -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/config.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/dataset/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/dataset/README.md -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/dataset/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/dataset/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/dataset/rl_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/dataset/rl_dataset.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/dataset/rm_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/dataset/rm_dataset.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/dataset/sft_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/dataset/sft_dataset.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/debug/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/debug/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/debug/performance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/debug/performance.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/debug/trajectory_tracker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/debug/trajectory_tracker.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/distributed.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/distributed.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/flops_counter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/flops_counter.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/fs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/fs.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/fsdp_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/fsdp_utils.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/hdfs_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/hdfs_io.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/import_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/import_utils.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/logger/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/logger/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/logger/aggregate_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/logger/aggregate_logger.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/logging_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/logging_utils.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/megatron/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/megatron/memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/megatron/memory.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/megatron/optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/megatron/optimizer.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/megatron/optimizer_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/megatron/optimizer_config.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/megatron/pipeline_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/megatron/pipeline_parallel.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/megatron/sequence_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/megatron/sequence_parallel.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/megatron/tensor_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/megatron/tensor_parallel.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/megatron_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/megatron_utils.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/memory_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/memory_buffer.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/model.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/py_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/py_functional.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/ray_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/ray_utils.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/rendezvous/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/rendezvous/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/rendezvous/ray_backend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/rendezvous/ray_backend.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/reward_score/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/reward_score/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/reward_score/countdown.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/reward_score/countdown.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/reward_score/gsm8k.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/reward_score/gsm8k.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/reward_score/kk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/reward_score/kk.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/reward_score/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/reward_score/math.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/reward_score/multiply.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/reward_score/multiply.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/seqlen_balancing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/seqlen_balancing.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/tokenizer.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/torch_dtypes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/torch_dtypes.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/torch_functional.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/tracking.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/tracking.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/utils/ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/utils/ulysses.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/version/version: -------------------------------------------------------------------------------- 1 | 0.1 -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/actor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/actor/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/actor/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/actor/base.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/actor/dp_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/actor/dp_actor.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/actor/megatron_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/actor/megatron_actor.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/critic/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/critic/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/critic/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/critic/base.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/critic/dp_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/critic/dp_critic.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/critic/megatron_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/critic/megatron_critic.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/fsdp_workers.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/megatron_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/megatron_workers.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/reward_model/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/reward_model/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/reward_model/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/reward_model/base.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/reward_model/megatron/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/reward_model/megatron/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/reward_model/megatron/reward_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/reward_model/megatron/reward_model.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/rollout/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/rollout/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/rollout/base.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/rollout/hf_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/rollout/hf_rollout.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/rollout/naive/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/rollout/naive/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/rollout/naive/naive_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/rollout/naive/naive_rollout.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/rollout/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/rollout/tokenizer.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/rollout/vllm_rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/rollout/vllm_rollout/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/rollout/vllm_rollout/vllm_rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/rollout/vllm_rollout/vllm_rollout.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/sharding_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/sharding_manager/__init__.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/sharding_manager/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/sharding_manager/base.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/sharding_manager/fsdp_ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/sharding_manager/fsdp_ulysses.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/sharding_manager/fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/sharding_manager/fsdp_vllm.py -------------------------------------------------------------------------------- /lab9/Logic-RL/verl/workers/sharding_manager/megatron_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/Logic-RL/verl/workers/sharding_manager/megatron_vllm.py -------------------------------------------------------------------------------- /lab9/task.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xuw/llm_course_public/HEAD/lab9/task.ipynb --------------------------------------------------------------------------------