├── .gitattributes ├── .github ├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── requirements-test.txt └── workflows │ └── tests.yml ├── .gitignore ├── .pre-commit-config.yaml ├── =4.51.0 ├── Dockerfile ├── Dockerfile.legacy ├── LICENSE ├── Makefile ├── README.md ├── assets ├── baselines.md ├── easyr1_grpo.png ├── qwen2_5_vl_7b_geo.png └── wechat.jpg ├── docs ├── Figure 11.pdf ├── Figure 2.png ├── logo.png ├── method.png └── overview.png ├── eval ├── eval_close.py └── eval_open.py ├── examples ├── baselines │ ├── qwen2_5_vl_3b_clevr.sh │ └── qwen2_5_vl_3b_geoqa8k.sh ├── config.yaml ├── format_prompt │ ├── close.jinja │ ├── dapo.jinja │ ├── math.jinja │ ├── open.jinja │ └── r1v.jinja ├── qwen2_5_vl_32b_geo3k_grpo.sh ├── qwen2_5_vl_7b_closeQA+think+ans_grpo.sh ├── qwen2_5_vl_7b_geo3k_dapo.sh ├── qwen2_5_vl_7b_geo3k_grpo.sh ├── qwen2_5_vl_7b_geo3k_reinforce.sh ├── qwen2_5_vl_7b_geo3k_swanlab.sh ├── qwen2_5_vl_7b_multi_image.sh ├── qwen2_5_vl_7b_openQA+think+ans_grpo.sh ├── qwen3_14b_dapo17k_dapo.sh ├── qwen3_4b_math_grpo.sh ├── reward_function │ ├── closeQA+think+ans.py │ ├── dapo.py │ ├── math.py │ ├── openQA+think+ans.py │ └── r1v.py └── runtime_env.yaml ├── generation_samples.txt ├── pyproject.toml ├── requirements.txt ├── scripts └── model_merger.py ├── setup.py ├── tests ├── check_license.py ├── test_dataproto.py └── test_dataset.py └── verl ├── __init__.py ├── models ├── __init__.py ├── monkey_patch.py └── transformers │ ├── __init__.py │ ├── flash_attention_utils.py │ └── qwen2_vl.py ├── protocol.py ├── single_controller ├── __init__.py ├── base │ ├── __init__.py │ ├── decorator.py │ ├── register_center │ │ ├── __init__.py │ │ └── ray.py │ ├── worker.py │ └── worker_group.py └── ray │ ├── __init__.py │ └── base.py ├── trainer ├── __init__.py ├── config.py ├── core_algos.py ├── data_loader.py ├── main.py ├── metrics.py └── ray_trainer.py ├── utils ├── __init__.py ├── checkpoint │ ├── __init__.py │ ├── checkpoint_manager.py │ └── fsdp_checkpoint_manager.py ├── dataset.py ├── flops_counter.py ├── fsdp_utils.py ├── logger │ ├── __init__.py │ ├── gen_logger.py │ └── logger.py ├── model_utils.py ├── py_functional.py ├── seqlen_balancing.py ├── tokenizer.py ├── torch_dtypes.py ├── torch_functional.py └── ulysses.py └── workers ├── __init__.py ├── actor ├── __init__.py ├── base.py ├── config.py └── dp_actor.py ├── config.py ├── critic ├── __init__.py ├── base.py ├── config.py └── dp_critic.py ├── fsdp_workers.py ├── reward ├── __init__.py ├── answer_only.py ├── config.py ├── function.py ├── function_open+think+ans.py ├── function_original.py └── function_wo_batch_acc.py ├── rollout ├── __init__.py ├── base.py ├── config.py └── vllm_rollout_spmd.py └── sharding_manager ├── __init__.py ├── base.py ├── fsdp_ulysses.py └── fsdp_vllm.py /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/.gitattributes -------------------------------------------------------------------------------- /.github/CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/.github/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /.github/CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/.github/CONTRIBUTING.md -------------------------------------------------------------------------------- /.github/requirements-test.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/.github/requirements-test.txt -------------------------------------------------------------------------------- /.github/workflows/tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/.github/workflows/tests.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/.gitignore -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /=4.51.0: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/=4.51.0 -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/Dockerfile -------------------------------------------------------------------------------- /Dockerfile.legacy: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/Dockerfile.legacy -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/LICENSE -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/Makefile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/README.md -------------------------------------------------------------------------------- /assets/baselines.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/assets/baselines.md -------------------------------------------------------------------------------- /assets/easyr1_grpo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/assets/easyr1_grpo.png -------------------------------------------------------------------------------- /assets/qwen2_5_vl_7b_geo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/assets/qwen2_5_vl_7b_geo.png -------------------------------------------------------------------------------- /assets/wechat.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/assets/wechat.jpg -------------------------------------------------------------------------------- /docs/Figure 11.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/docs/Figure 11.pdf -------------------------------------------------------------------------------- /docs/Figure 2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/docs/Figure 2.png -------------------------------------------------------------------------------- /docs/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/docs/logo.png -------------------------------------------------------------------------------- /docs/method.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/docs/method.png -------------------------------------------------------------------------------- /docs/overview.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/docs/overview.png -------------------------------------------------------------------------------- /eval/eval_close.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/eval/eval_close.py -------------------------------------------------------------------------------- /eval/eval_open.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/eval/eval_open.py -------------------------------------------------------------------------------- /examples/baselines/qwen2_5_vl_3b_clevr.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/baselines/qwen2_5_vl_3b_clevr.sh -------------------------------------------------------------------------------- /examples/baselines/qwen2_5_vl_3b_geoqa8k.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/baselines/qwen2_5_vl_3b_geoqa8k.sh -------------------------------------------------------------------------------- /examples/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/config.yaml -------------------------------------------------------------------------------- /examples/format_prompt/close.jinja: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/format_prompt/close.jinja -------------------------------------------------------------------------------- /examples/format_prompt/dapo.jinja: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/format_prompt/dapo.jinja -------------------------------------------------------------------------------- /examples/format_prompt/math.jinja: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/format_prompt/math.jinja -------------------------------------------------------------------------------- /examples/format_prompt/open.jinja: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/format_prompt/open.jinja -------------------------------------------------------------------------------- /examples/format_prompt/r1v.jinja: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/format_prompt/r1v.jinja -------------------------------------------------------------------------------- /examples/qwen2_5_vl_32b_geo3k_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/qwen2_5_vl_32b_geo3k_grpo.sh -------------------------------------------------------------------------------- /examples/qwen2_5_vl_7b_closeQA+think+ans_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/qwen2_5_vl_7b_closeQA+think+ans_grpo.sh -------------------------------------------------------------------------------- /examples/qwen2_5_vl_7b_geo3k_dapo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/qwen2_5_vl_7b_geo3k_dapo.sh -------------------------------------------------------------------------------- /examples/qwen2_5_vl_7b_geo3k_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/qwen2_5_vl_7b_geo3k_grpo.sh -------------------------------------------------------------------------------- /examples/qwen2_5_vl_7b_geo3k_reinforce.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/qwen2_5_vl_7b_geo3k_reinforce.sh -------------------------------------------------------------------------------- /examples/qwen2_5_vl_7b_geo3k_swanlab.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/qwen2_5_vl_7b_geo3k_swanlab.sh -------------------------------------------------------------------------------- /examples/qwen2_5_vl_7b_multi_image.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/qwen2_5_vl_7b_multi_image.sh -------------------------------------------------------------------------------- /examples/qwen2_5_vl_7b_openQA+think+ans_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/qwen2_5_vl_7b_openQA+think+ans_grpo.sh -------------------------------------------------------------------------------- /examples/qwen3_14b_dapo17k_dapo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/qwen3_14b_dapo17k_dapo.sh -------------------------------------------------------------------------------- /examples/qwen3_4b_math_grpo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/qwen3_4b_math_grpo.sh -------------------------------------------------------------------------------- /examples/reward_function/closeQA+think+ans.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/reward_function/closeQA+think+ans.py -------------------------------------------------------------------------------- /examples/reward_function/dapo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/reward_function/dapo.py -------------------------------------------------------------------------------- /examples/reward_function/math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/reward_function/math.py -------------------------------------------------------------------------------- /examples/reward_function/openQA+think+ans.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/reward_function/openQA+think+ans.py -------------------------------------------------------------------------------- /examples/reward_function/r1v.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/reward_function/r1v.py -------------------------------------------------------------------------------- /examples/runtime_env.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/examples/runtime_env.yaml -------------------------------------------------------------------------------- /generation_samples.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/generation_samples.txt -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/pyproject.toml -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/requirements.txt -------------------------------------------------------------------------------- /scripts/model_merger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/scripts/model_merger.py -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/setup.py -------------------------------------------------------------------------------- /tests/check_license.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/tests/check_license.py -------------------------------------------------------------------------------- /tests/test_dataproto.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/tests/test_dataproto.py -------------------------------------------------------------------------------- /tests/test_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/tests/test_dataset.py -------------------------------------------------------------------------------- /verl/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/__init__.py -------------------------------------------------------------------------------- /verl/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/models/__init__.py -------------------------------------------------------------------------------- /verl/models/monkey_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/models/monkey_patch.py -------------------------------------------------------------------------------- /verl/models/transformers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/models/transformers/__init__.py -------------------------------------------------------------------------------- /verl/models/transformers/flash_attention_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/models/transformers/flash_attention_utils.py -------------------------------------------------------------------------------- /verl/models/transformers/qwen2_vl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/models/transformers/qwen2_vl.py -------------------------------------------------------------------------------- /verl/protocol.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/protocol.py -------------------------------------------------------------------------------- /verl/single_controller/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/single_controller/__init__.py -------------------------------------------------------------------------------- /verl/single_controller/base/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/single_controller/base/__init__.py -------------------------------------------------------------------------------- /verl/single_controller/base/decorator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/single_controller/base/decorator.py -------------------------------------------------------------------------------- /verl/single_controller/base/register_center/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/single_controller/base/register_center/__init__.py -------------------------------------------------------------------------------- /verl/single_controller/base/register_center/ray.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/single_controller/base/register_center/ray.py -------------------------------------------------------------------------------- /verl/single_controller/base/worker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/single_controller/base/worker.py -------------------------------------------------------------------------------- /verl/single_controller/base/worker_group.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/single_controller/base/worker_group.py -------------------------------------------------------------------------------- /verl/single_controller/ray/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/single_controller/ray/__init__.py -------------------------------------------------------------------------------- /verl/single_controller/ray/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/single_controller/ray/base.py -------------------------------------------------------------------------------- /verl/trainer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/trainer/__init__.py -------------------------------------------------------------------------------- /verl/trainer/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/trainer/config.py -------------------------------------------------------------------------------- /verl/trainer/core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/trainer/core_algos.py -------------------------------------------------------------------------------- /verl/trainer/data_loader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/trainer/data_loader.py -------------------------------------------------------------------------------- /verl/trainer/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/trainer/main.py -------------------------------------------------------------------------------- /verl/trainer/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/trainer/metrics.py -------------------------------------------------------------------------------- /verl/trainer/ray_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/trainer/ray_trainer.py -------------------------------------------------------------------------------- /verl/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/__init__.py -------------------------------------------------------------------------------- /verl/utils/checkpoint/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/checkpoint/__init__.py -------------------------------------------------------------------------------- /verl/utils/checkpoint/checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/checkpoint/checkpoint_manager.py -------------------------------------------------------------------------------- /verl/utils/checkpoint/fsdp_checkpoint_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/checkpoint/fsdp_checkpoint_manager.py -------------------------------------------------------------------------------- /verl/utils/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/dataset.py -------------------------------------------------------------------------------- /verl/utils/flops_counter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/flops_counter.py -------------------------------------------------------------------------------- /verl/utils/fsdp_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/fsdp_utils.py -------------------------------------------------------------------------------- /verl/utils/logger/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/logger/__init__.py -------------------------------------------------------------------------------- /verl/utils/logger/gen_logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/logger/gen_logger.py -------------------------------------------------------------------------------- /verl/utils/logger/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/logger/logger.py -------------------------------------------------------------------------------- /verl/utils/model_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/model_utils.py -------------------------------------------------------------------------------- /verl/utils/py_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/py_functional.py -------------------------------------------------------------------------------- /verl/utils/seqlen_balancing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/seqlen_balancing.py -------------------------------------------------------------------------------- /verl/utils/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/tokenizer.py -------------------------------------------------------------------------------- /verl/utils/torch_dtypes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/torch_dtypes.py -------------------------------------------------------------------------------- /verl/utils/torch_functional.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/torch_functional.py -------------------------------------------------------------------------------- /verl/utils/ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/utils/ulysses.py -------------------------------------------------------------------------------- /verl/workers/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/__init__.py -------------------------------------------------------------------------------- /verl/workers/actor/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/actor/__init__.py -------------------------------------------------------------------------------- /verl/workers/actor/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/actor/base.py -------------------------------------------------------------------------------- /verl/workers/actor/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/actor/config.py -------------------------------------------------------------------------------- /verl/workers/actor/dp_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/actor/dp_actor.py -------------------------------------------------------------------------------- /verl/workers/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/config.py -------------------------------------------------------------------------------- /verl/workers/critic/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/critic/__init__.py -------------------------------------------------------------------------------- /verl/workers/critic/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/critic/base.py -------------------------------------------------------------------------------- /verl/workers/critic/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/critic/config.py -------------------------------------------------------------------------------- /verl/workers/critic/dp_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/critic/dp_critic.py -------------------------------------------------------------------------------- /verl/workers/fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/fsdp_workers.py -------------------------------------------------------------------------------- /verl/workers/reward/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/reward/__init__.py -------------------------------------------------------------------------------- /verl/workers/reward/answer_only.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/reward/answer_only.py -------------------------------------------------------------------------------- /verl/workers/reward/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/reward/config.py -------------------------------------------------------------------------------- /verl/workers/reward/function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/reward/function.py -------------------------------------------------------------------------------- /verl/workers/reward/function_open+think+ans.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/reward/function_open+think+ans.py -------------------------------------------------------------------------------- /verl/workers/reward/function_original.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/reward/function_original.py -------------------------------------------------------------------------------- /verl/workers/reward/function_wo_batch_acc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/reward/function_wo_batch_acc.py -------------------------------------------------------------------------------- /verl/workers/rollout/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/rollout/__init__.py -------------------------------------------------------------------------------- /verl/workers/rollout/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/rollout/base.py -------------------------------------------------------------------------------- /verl/workers/rollout/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/rollout/config.py -------------------------------------------------------------------------------- /verl/workers/rollout/vllm_rollout_spmd.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/rollout/vllm_rollout_spmd.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/sharding_manager/__init__.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/sharding_manager/base.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/fsdp_ulysses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/sharding_manager/fsdp_ulysses.py -------------------------------------------------------------------------------- /verl/workers/sharding_manager/fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/SII-WenjieLisjtu/CX-Mind/HEAD/verl/workers/sharding_manager/fsdp_vllm.py --------------------------------------------------------------------------------