Wheelodex » Projects » openrlhf

openrlhf

View on PyPI — Reverse Dependencies (0)

0.5.1 openrlhf-0.5.1-cp311-cp311-manylinux1_x86_64.whl
openrlhf-0.5.1-cp310-cp310-manylinux1_x86_64.whl
0.5.0 openrlhf-0.5.0-cp311-cp311-manylinux1_x86_64.whl
openrlhf-0.5.0-cp310-cp310-manylinux1_x86_64.whl

Wheel Details

Project: openrlhf
Version: 0.5.0
Filename: openrlhf-0.5.0-cp311-cp311-manylinux1_x86_64.whl
Download: [link]
Size: 126807
MD5: 75fe6fe8ae9c5138e3051100bcdbbd45
SHA256: bf311d564a53a51ac4bd17d782ddbbf00eb5f3371d15cd610bcaa748756b5274
Uploaded: 2024-11-07 10:28:09 +0000

dist-info

METADATA · WHEEL · RECORD · top_level.txt

METADATA

Metadata-Version: 2.1
Name: openrlhf
Version: 0.5.0
Summary: A Ray-based High-performance RLHF framework.
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Environment :: GPU :: NVIDIA CUDA
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: System :: Distributed Computing
Requires-Python: >=3.10
Requires-Dist: accelerate
Requires-Dist: bitsandbytes
Requires-Dist: datasets
Requires-Dist: deepspeed (==0.15.0)
Requires-Dist: einops
Requires-Dist: flash-attn (==2.6.1)
Requires-Dist: isort
Requires-Dist: jsonlines
Requires-Dist: loralib
Requires-Dist: optimum
Requires-Dist: packaging
Requires-Dist: peft
Requires-Dist: ray[default] (==2.12.0)
Requires-Dist: tensorboard
Requires-Dist: torch
Requires-Dist: torchmetrics
Requires-Dist: tqdm
Requires-Dist: transformers (==4.46.1)
Requires-Dist: transformers-stream-generator
Requires-Dist: wandb
Requires-Dist: wheel
Requires-Dist: vllm (==0.4.2); extra == "vllm"
Requires-Dist: vllm (>0.4.2); extra == "vllm-latest"
Provides-Extra: vllm
Provides-Extra: vllm_latest
Description-Content-Type: text/markdown
License-File: LICENSE
[Description omitted; length: 18682 characters]

WHEEL

Wheel-Version: 1.0
Generator: bdist_wheel (0.44.0)
Root-Is-Purelib: false
Tag: cp311-cp311-manylinux1_x86_64

RECORD

Path Digest Size
openrlhf-0.5.0.data/purelib/openrlhf/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
openrlhf-0.5.0.data/purelib/openrlhf/cli/__init__.py sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU 0
openrlhf-0.5.0.data/purelib/openrlhf/cli/batch_inference.py sha256=ZtwvAYaqjsVN8biqLUwKRAo_28cIHICX60W9Is3di08 13926
openrlhf-0.5.0.data/purelib/openrlhf/cli/interactive_chat.py sha256=HsQeVhOfk-FphDYyZ5WDyEUinLdo_PHxztBR0dOXCyA 4302
openrlhf-0.5.0.data/purelib/openrlhf/cli/serve_rm.py sha256=Ms8-QY6jer6RalDA14TNvvW5cNxs0fkzhLYPv7DGbv0 4208
openrlhf-0.5.0.data/purelib/openrlhf/cli/train_dpo.py sha256=pQEiuMkscKWbwSeqTE-dQmf7HOLyvWORScI0TpPnFxY 11287
openrlhf-0.5.0.data/purelib/openrlhf/cli/train_kd.py sha256=xEf9yA_GxyY_tSG65FBJs4w4mGMIekRRs6uNtg6xq9Q 9359
openrlhf-0.5.0.data/purelib/openrlhf/cli/train_kto.py sha256=3fkBlDAbJS5to6NjsAbY5AfldfOepQAbOZhpXUYhrkE 9399
openrlhf-0.5.0.data/purelib/openrlhf/cli/train_ppo.py sha256=OAvqLnECkjesIUO-prTplJgXaTmTAyhJqDTzsXJ5V1Q 16920
openrlhf-0.5.0.data/purelib/openrlhf/cli/train_ppo_ray.py sha256=54P1_9B9dzRIQ-MhFjvjIfv08maPAFhBEAj0nBcp9LU 17184
openrlhf-0.5.0.data/purelib/openrlhf/cli/train_prm.py sha256=b_j0r6jRtzz4Q_1WNIFfGcKjonA4ajn6vnavBh7KXwg 8933
openrlhf-0.5.0.data/purelib/openrlhf/cli/train_rm.py sha256=INKyjJ9EONgp5eG9-7i4h0PhQ7Z-vHdsQNdAnNMq0eE 10424
openrlhf-0.5.0.data/purelib/openrlhf/cli/train_sft.py sha256=JZ0yxwA6IlVAegrl9pl_-PRNZjOTnqVxZQ7CoVVuwPM 9540
openrlhf-0.5.0.data/purelib/openrlhf/datasets/__init__.py sha256=l3wBBZXsbrnhKtOB0eR-oGI_SeO3MsYEPFAvh3VGZB8 245
openrlhf-0.5.0.data/purelib/openrlhf/datasets/process_reward_dataset.py sha256=0dgYmQYwrNvmDMPkWNwT7lPXqdRypwB4OwnXHXZuOMQ 4773
openrlhf-0.5.0.data/purelib/openrlhf/datasets/prompts_dataset.py sha256=0FkahFZn3j4dIx_0LmGpakMIVEDvTcW1P4kyqGSWVS8 1739
openrlhf-0.5.0.data/purelib/openrlhf/datasets/reward_dataset.py sha256=a0ielgZkfYdQV3HSQe6sKj450HsfeeNWc_pfzmRQq08 8611
openrlhf-0.5.0.data/purelib/openrlhf/datasets/sft_dataset.py sha256=oq4rJmqt9v5Aubm_pSeaBsa-3swMedgXEyRFYwFx51A 6448
openrlhf-0.5.0.data/purelib/openrlhf/datasets/unpaired_preference_dataset.py sha256=x29425FkYRfrF5a9TXXBCZI0Uu7fgGDYdXJii3JBImg 5726
openrlhf-0.5.0.data/purelib/openrlhf/datasets/utils.py sha256=CrcY5A7N7eHz7vLtFo7-GD-ydTaXBgVh8r8PPSUoMfU 585
openrlhf-0.5.0.data/purelib/openrlhf/models/__init__.py sha256=SVRzZmnsOwe5QlLR2i5IVcmLKbMeMkmzEH4StWBDqpw 249
openrlhf-0.5.0.data/purelib/openrlhf/models/actor.py sha256=btSr7PXfrpXbLBp-W2T3KOBu3rdJzx1aXs0MAQfBIyM 9413
openrlhf-0.5.0.data/purelib/openrlhf/models/loss.py sha256=cEx-E9UmlHEP8e1Iwd2StTPrM9z6pxkduDl1MqnOITQ 11255
openrlhf-0.5.0.data/purelib/openrlhf/models/model.py sha256=P4RevTFrG_lWGn9AoGbcWRNVFpto7qSybKKVsSPjUzc 11655
openrlhf-0.5.0.data/purelib/openrlhf/models/ring_attn_utils.py sha256=7yd-_1K9EP5VE4uTcsEsLkXhDOI0Ne800bFx7TvqozU 2590
openrlhf-0.5.0.data/purelib/openrlhf/models/utils.py sha256=EAMTmvFk_p2yWvL9ACA4oC7YKadlA0XU5LsvMVfBR00 4277
openrlhf-0.5.0.data/purelib/openrlhf/trainer/__init__.py sha256=fMnpIziivdlJSftRDIXiqUkf31HJ2MWak7cJ-fMwBX4 272
openrlhf-0.5.0.data/purelib/openrlhf/trainer/dpo_trainer.py sha256=UjGvmzGe12k9Of05BOWEWvvbxGNrrRGKQNcUIJq0HBw 21055
openrlhf-0.5.0.data/purelib/openrlhf/trainer/kd_trainer.py sha256=Xo9gIk9PN4XRWMSz4GnFv48puaE0XwgHkZiCetSm5G4 10244
openrlhf-0.5.0.data/purelib/openrlhf/trainer/kto_trainer.py sha256=1p9CJte1k-vWswhbF-Z4k2QfmO6mqI5_5Vh8H7N-Qfk 14260
openrlhf-0.5.0.data/purelib/openrlhf/trainer/ppo_trainer.py sha256=cWgA8o9xFCH98O4YgJWk_YZn8VhxS5L4S7ve1pnTQ6k 20623
openrlhf-0.5.0.data/purelib/openrlhf/trainer/prm_trainer.py sha256=OXJzaa3lZBliI47Wiwz0xJ0HYB-i90TDAYiMW0VdN1M 9893
openrlhf-0.5.0.data/purelib/openrlhf/trainer/rm_trainer.py sha256=AvdVEevUOVaYpUDmFY4FrIoeGiDrFLdgEt-A0d8oK9M 16092
openrlhf-0.5.0.data/purelib/openrlhf/trainer/sft_trainer.py sha256=gUzoZGsn5Uuj3ihggW-cZZdsnNfAYu0FXXwNxEMn5UU 11407
openrlhf-0.5.0.data/purelib/openrlhf/trainer/ppo_utils/__init__.py sha256=8cK-pZd7WwO14h6at9EA_Oj-QLUK_x1doM51ayFvWBw 198
openrlhf-0.5.0.data/purelib/openrlhf/trainer/ppo_utils/experience_maker.py sha256=946doo3vFi0JDn_d4FuEH9bHRzHuK-LuyQ5FspSjMYs 26155
openrlhf-0.5.0.data/purelib/openrlhf/trainer/ppo_utils/kl_controller.py sha256=nzcvDrFUDuysAnwJR5SWek8Hwv-K2l49cL7std-FaGA 738
openrlhf-0.5.0.data/purelib/openrlhf/trainer/ppo_utils/replay_buffer.py sha256=QnjNCU6UOs5U4Nq93hPfMsfkQgbLTQ0eUqrPxRnE2L0 7574
openrlhf-0.5.0.data/purelib/openrlhf/trainer/ray/__init__.py sha256=jzfMQ4LLoEOvsps9H7pT_TjAn5KyuIT5xnwp5_wRfCs 241
openrlhf-0.5.0.data/purelib/openrlhf/trainer/ray/launcher.py sha256=toGWkWSAUEqr6IFEMyOqltUULmbgwe08CT6-EtYV1RE 12435
openrlhf-0.5.0.data/purelib/openrlhf/trainer/ray/ppo_actor.py sha256=WszrWRxve4RB35AqGNUV57yWMKyOi1JzgYaFHLMe-PY 15135
openrlhf-0.5.0.data/purelib/openrlhf/trainer/ray/ppo_critic.py sha256=TyP__9kChU_NLHP7o6UfaXKQRd6dbbK4FoACdKGT49Q 7132
openrlhf-0.5.0.data/purelib/openrlhf/trainer/ray/vllm_engine.py sha256=HJiig-0Ck642xiIHc0610jWDiblljyCl5577QFxvbUM 4694
openrlhf-0.5.0.data/purelib/openrlhf/trainer/ray/vllm_worker_wrap.py sha256=f9PU09TF_J9o58UaU3aLSiILpIZHLj0w-7HHU537jFc 1873
openrlhf-0.5.0.data/purelib/openrlhf/utils/__init__.py sha256=2L_K3fD6o1REMQ8LUNc9Xnqh3ad1AyeuvR97QpTdUxc 166
openrlhf-0.5.0.data/purelib/openrlhf/utils/deepspeed.py sha256=ODmkbgnjXJxPM9ajHAHw17i1BCs3_jXAA7O6P91_xlc 16991
openrlhf-0.5.0.data/purelib/openrlhf/utils/deepspeed_utils.py sha256=4VhNS6FmBl4Ii6SoGXAOwASYxYwLDSDUWlSVld4Vfwk 3115
openrlhf-0.5.0.data/purelib/openrlhf/utils/distributed_sampler.py sha256=WgmRlcY-R19C_RfkO0xA7REzrDI39iNBC-__zJAFzac 6482
openrlhf-0.5.0.data/purelib/openrlhf/utils/distributed_util.py sha256=QLTxvaV6mNZvnucyuZLKegqr7ae3bR2BlDGq_iiPQXo 2347
openrlhf-0.5.0.data/purelib/openrlhf/utils/logging_utils.py sha256=Ph1HPTiuqllCugM5jXCxB_3Ts-LnGEED2AYCo8eGBto 1796
openrlhf-0.5.0.data/purelib/openrlhf/utils/processor.py sha256=3n9ya135UGqr2ey5uzxlfFPV7vhODekxyVmJAgm1e-k 3093
openrlhf-0.5.0.data/purelib/openrlhf/utils/remote_rm_utils.py sha256=1-0y0MKlMGLuzlcYiHfboSKQHA0xVfk1oH7gDiNlgog 1725
openrlhf-0.5.0.data/purelib/openrlhf/utils/utils.py sha256=4SgEvbF8t2kGXMJ69NdW1rEDJHtz_CdBBmIcHFwV_S4 4578
openrlhf-0.5.0.dist-info/LICENSE sha256=QwcOLU5TJoTeUhuIXzhdCEEDDvorGiC6-3YTOl4TecE 11356
openrlhf-0.5.0.dist-info/METADATA sha256=kPo9N6a5Ap68ODUn5vtQRJ17_4lDDvswrw0pYPlEXqE 19968
openrlhf-0.5.0.dist-info/WHEEL sha256=Vd5A18-d2wZAY8WDmgxtOE2bK9Ob_vQGjJ7aeTWaXz4 110
openrlhf-0.5.0.dist-info/top_level.txt sha256=PKhp5t7FXoRFbYrUoMcbRiF_qVRlj4NRLGQYc4M3axY 9
openrlhf-0.5.0.dist-info/RECORD — —

top_level.txt

openrlhf