Wheelodex » Projects » trl

trl

View on PyPI — Reverse Dependencies (70)

0.13.0 trl-0.13.0-py3-none-any.whl

Wheel Details

Project: trl
Version: 0.13.0
Filename: trl-0.13.0-py3-none-any.whl
Download: [link]
Size: 293448
MD5: 00d59405374caed145e60795a110187b
SHA256: 792aa68a98821934a890182c842f9f8b43127eea510a7c2bd660a10bc59de7e8
Uploaded: 2024-12-16 15:14:49 +0000

dist-info

METADATA · WHEEL · RECORD · top_level.txt · entry_points.txt

METADATA

Metadata-Version: 2.1
Name: trl
Version: 0.13.0
Summary: Train transformer language models with reinforcement learning.
Author: Leandro von Werra
Author-Email: leandro.vonwerra[at]gmail.com
Home-Page: https://github.com/huggingface/trl
License: Apache 2.0
Keywords: ppo,transformers,huggingface,gpt2,language modeling,rlhf
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Requires-Python: >=3.9
Requires-Dist: accelerate (>=0.34.0)
Requires-Dist: datasets (>=2.21.0)
Requires-Dist: rich
Requires-Dist: transformers (>=4.46.0)
Requires-Dist: deepspeed (>=0.14.4); sys_platform != "win32" and extra == "deepspeed"
Requires-Dist: diffusers (>=0.18.0); extra == "diffusers"
Requires-Dist: openai (>=1.23.2); extra == "judges"
Requires-Dist: llm-blender (>=0.0.2); extra == "judges"
Requires-Dist: liger-kernel (>=0.4.0); sys_platform != "win32" and extra == "liger"
Requires-Dist: mergekit (>=0.0.5.1); extra == "mergekit"
Requires-Dist: peft (>=0.8.0); extra == "peft"
Requires-Dist: bitsandbytes; extra == "quantization"
Requires-Dist: scikit-learn; extra == "scikit"
Requires-Dist: parameterized; extra == "test"
Requires-Dist: pytest-cov; extra == "test"
Requires-Dist: pytest-rerunfailures; extra == "test"
Requires-Dist: pytest-xdist; extra == "test"
Requires-Dist: pytest; extra == "test"
Requires-Dist: Pillow; extra == "vlm"
Requires-Dist: deepspeed (>=0.14.4); sys_platform != "win32" and extra == "dev"
Requires-Dist: diffusers (>=0.18.0); extra == "dev"
Requires-Dist: openai (>=1.23.2); extra == "dev"
Requires-Dist: llm-blender (>=0.0.2); extra == "dev"
Requires-Dist: liger-kernel (>=0.4.0); sys_platform != "win32" and extra == "dev"
Requires-Dist: mergekit (>=0.0.5.1); extra == "dev"
Requires-Dist: peft (>=0.8.0); extra == "dev"
Requires-Dist: bitsandbytes; extra == "dev"
Requires-Dist: scikit-learn; extra == "dev"
Requires-Dist: parameterized; extra == "dev"
Requires-Dist: pytest-cov; extra == "dev"
Requires-Dist: pytest-rerunfailures; extra == "dev"
Requires-Dist: pytest-xdist; extra == "dev"
Requires-Dist: pytest; extra == "dev"
Requires-Dist: Pillow; extra == "dev"
Requires-Dist: deepspeed (>=0.14.4); sys_platform != "win32" and extra == "dev"
Requires-Dist: diffusers (>=0.18.0); extra == "dev"
Requires-Dist: openai (>=1.23.2); extra == "dev"
Requires-Dist: llm-blender (>=0.0.2); extra == "dev"
Requires-Dist: liger-kernel (>=0.4.0); sys_platform != "win32" and extra == "dev"
Requires-Dist: mergekit (>=0.0.5.1); extra == "dev"
Requires-Dist: peft (>=0.8.0); extra == "dev"
Requires-Dist: bitsandbytes; extra == "dev"
Requires-Dist: scikit-learn; extra == "dev"
Requires-Dist: parameterized; extra == "dev"
Requires-Dist: pytest-cov; extra == "dev"
Requires-Dist: pytest-rerunfailures; extra == "dev"
Requires-Dist: pytest-xdist; extra == "dev"
Requires-Dist: pytest; extra == "dev"
Requires-Dist: Pillow; extra == "dev"
Provides-Extra: deepspeed
Provides-Extra: diffusers
Provides-Extra: judges
Provides-Extra: liger
Provides-Extra: mergekit
Provides-Extra: peft
Provides-Extra: quantization
Provides-Extra: scikit
Provides-Extra: test
Provides-Extra: vlm
Provides-Extra: dev
Description-Content-Type: text/markdown
License-File: LICENSE
[Description omitted; length: 8236 characters]

WHEEL

Wheel-Version: 1.0
Generator: setuptools (75.6.0)
Root-Is-Purelib: true
Tag: py3-none-any

RECORD

Path Digest Size
trl/__init__.py sha256=i9eeMZQLytclLFju8WhMuAxcSKUqaSfWlKXtv35-E9M 6121
trl/cli.py sha256=iksK9lFKEFrcH5jnfj5iRA2U0Z_5foZ8LpT2gdzFA84 3092
trl/core.py sha256=hNLGrX7ZIY3nKPBZ9OGkVokORhnuQpmFhX90eZMo0DQ 11404
trl/data_utils.py sha256=OsVSzbj7KaY1540QT-mWUowSy-YzVpsYuYOV2g26F0I 17312
trl/import_utils.py sha256=0ksoJzWgTF42NKi7tcBosdS11FtWQnA6rspdo-PENhc 4276
trl/mergekit_utils.py sha256=BaZKhWIpyaD3W1a0s07I7Es8QhcOTFq7t9yTGShV4KU 11104
trl/environment/__init__.py sha256=vrBTuQYZ1YC0bQchArhOR7xmPYV3Z_UvMHS-HG64xnA 984
trl/environment/base_environment.py sha256=QkwoGtYRGrcDfxndPPbLNDyqH0KIQ1X35CWKCKzh7y4 17872
trl/extras/__init__.py sha256=TdJe00vrvjRxCMSTqEBiEuBPFAMIObSdNufHfCSt2tU 956
trl/extras/best_of_n_sampler.py sha256=no-vcdr4VlRU-DSyn9vXWHIK1gnD-goFmg2aF04c1wU 5783
trl/extras/dataset_formatting.py sha256=TWvNFdKMdvyraALg86LIpNG9-KdMz8EW_WyAD7cVHjY 4463
trl/models/__init__.py sha256=eM2n7IT2Zlvctk3AuFDhg6CP_0NCsegXHFuXnV_m8dU 2236
trl/models/auxiliary_modules.py sha256=CW9gUU6MISC-djFFl8Pb1OZNgRXqpXi7pbGGHIsyLhg 3339
trl/models/modeling_base.py sha256=p7aIaF8bKK_fDzFrNZ-oJOeBQtLwY9TdMmYC2b6uBuw 30861
trl/models/modeling_sd_base.py sha256=oER9_JUG36mB4mElFHkSMcIQyy_1UKlApZAkQVim9PI 42261
trl/models/modeling_value_head.py sha256=ZtOdnFs80DQvSKKROU9A8DpO1lGMQ4BpsPEX4Y42MYA 18854
trl/models/sd_utils.py sha256=lr-DZHcUscgw0zqesxaCIL2YimnWtVtULp7OKN6FEO4 5874
trl/models/utils.py sha256=wT1Nq9GmrsyzDkxJlDFahQcGeVF1dGUU_ltPwSr4Joc 7465
trl/scripts/__init__.py sha256=K3BU-3vo4vcrh6MediZD-wgJMcyM3PIHJr9zeUOW_ww 998
trl/scripts/chat.py sha256=lNnY9yUb5CNIP1RK5IepAsjp-8vHUcq0W2bEVTpFEOE 17472
trl/scripts/dpo.py sha256=dEGsZVU_wEtV7Mjv9YMjd2U9LkcUE8Zm2S1_O8ktXKs 5052
trl/scripts/env.py sha256=vrvJ3vClD4Am4TQ5AqpXU-7lJ75tV1JaffUuFnOsd7g 3248
trl/scripts/kto.py sha256=R9KAy1u2I2-4gMHYKlNfb-UGQ9kdTHKMOnkdmcZdyw8 4116
trl/scripts/sft.py sha256=ByxreiB8nQXIxZdmtH4Fkls2BWXScaX4FQYoyayWMMA 3982
trl/scripts/utils.py sha256=oGlNJ9Xpi4usdOm_CIkruFunt4RpCkKT4rlbLkMwcxI 11198
trl/templates/lm_model_card.md sha256=IzX3BijfGyZzJRoXZ7qc2BBe4qw5SBPm0Z_Fzfk1YTM 2155
trl/trainer/__init__.py sha256=GmymfBH1dGPfv4DHPzQ9tJl1W3a9xvWsPMiEFqaGS28 5638
trl/trainer/alignprop_config.py sha256=ToXQbwwsERqa48-XgMkZF9csGm2v3sC_mHi_Oy3jMB4 6948
trl/trainer/alignprop_trainer.py sha256=XTIz4BInGtWHA7dG9bQZE7_0VrZayhjW4BDd8iCwRXk 18239
trl/trainer/base.py sha256=yjWNIybB3jBFieI2XN1zPkSTUXqpkKCeYT9Jx-EBdMo 1772
trl/trainer/bco_config.py sha256=ZQq7xSphyKXH1Sv_1NmtYvxEbKn1t6Ul3qjz3JGnagU 5068
trl/trainer/bco_trainer.py sha256=o6ycNf1PMxIMt1ffpZBD7hXJGqJSu6WIIWzQyBYziH0 72271
trl/trainer/callbacks.py sha256=ZYZHgv4ZH1UbpICdvSyGFILZGx1RLvk5l-Esehjd-vE 24064
trl/trainer/cpo_config.py sha256=xUZ4mdHhtD-OgKth1iA9yv7NGMc3NWQqSDQN0htfqtk 5551
trl/trainer/cpo_trainer.py sha256=TYrSAJ9u92tbEqfNaHZlB5lb6-z0mLTgefS7qNt_AsM 49907
trl/trainer/ddpo_config.py sha256=Nu5RRFWuopcY1vUAZyRyE8zo-YlZ3--ePEYzeqoEtsA 8160
trl/trainer/ddpo_trainer.py sha256=5hxVVBwgJquoQhY1bT6MXV8L8B4icOCyP32QAEAKZw8 27939
trl/trainer/dpo_config.py sha256=ylRcuogSkVe4jqRCtsnwwXcPj5DUZ9PBhpy1zXlnqYM 12822
trl/trainer/dpo_trainer.py sha256=cGS33VLayGsLhF2Pn_VtwibM0gKfsJC5yWfzO90niD8 76140
trl/trainer/gkd_config.py sha256=hKTD_Vd40pgU8z8i4Uuy3J67O5Qy-lMdnuQI6zfBT-s 3031
trl/trainer/gkd_trainer.py sha256=qo2cv9B9goiujFw7ph547KFsWpGQRng1sOvyAiEXTyU 17095
trl/trainer/iterative_sft_trainer.py sha256=rTXGkgexOO_pIUpI01oY9u5fPrtdTSXLBSzDH1xwoeM 18832
trl/trainer/judges.py sha256=oGIBVsspWEkfZJI8Xz4J1Oji9JBAVZKmAqtqRLNNRTM 19558
trl/trainer/kto_config.py sha256=5KIxgZZqY47pZc8CZH3pRr4RIoV0coUgT0AZQ06YFe8 5740
trl/trainer/kto_trainer.py sha256=ofCeTiz57Dk10H9RzavklkMUNKL5bLq1uJGk92qTp5A 74485
trl/trainer/model_config.py sha256=7hoeDUOL5FOiBtFhDN7cMFRDmT5FP1glLz6CGKTPW68 4955
trl/trainer/nash_md_config.py sha256=t-Xu0BuCHMjFGEDr0eAnHL-CUUVaMOsJ7mGw0MBtByA 1528
trl/trainer/nash_md_trainer.py sha256=FmA7No1EGiIlZQCwo5VAhl_BhX0rgcBM27ub9rCenjE 22609
trl/trainer/online_dpo_config.py sha256=VUz7tBGOYPYBpsu_ds-QRXMEShNfCljZDRru8JsaSpI 3937
trl/trainer/online_dpo_trainer.py sha256=pY7qAoJVhdgx--P4rxLQwb4Mf-ENpQ7v18JS0Q8zxYo 35635
trl/trainer/orpo_config.py sha256=eUBK88xz65xZid5dxQDin_PW8Fe4Zu5f48lq7cPFbUM 4309
trl/trainer/orpo_trainer.py sha256=bPUDfH-nk1QPrYII6UhRWgxBYxYctmeJU8oKUXNcWJ0 51510
trl/trainer/ppo_config.py sha256=m795so3POzwxzxNcj-3a5dytQr1tnxWBiNLu3zWC4UU 2824
trl/trainer/ppo_trainer.py sha256=PlayMLwb3uP7df7vi6eyCU15yaGLh68pE0HMx9UmcAA 39128
trl/trainer/prm_config.py sha256=vEeZl36bJFG3F8FuC0V0Z4-m0Q-XpTKI5rUQza64wWI 2245
trl/trainer/prm_trainer.py sha256=a02PsJmduGuoGb5TuGMM4KQRwQdADXWrWaIf2aWsGv0 15598
trl/trainer/reward_config.py sha256=n4L091qDbptyO-YlWipFwoaRt5PBOXV2_zI_QhckI7Q 2095
trl/trainer/reward_trainer.py sha256=oCUNW6VnL2wzxOX--x-8fuqdUfLuqXnBFL2qOU5GrFc 19155
trl/trainer/rloo_config.py sha256=IcVCKicP_e_cZ044AMHurDlf_bDzKLf1plsmkbOAacs 2052
trl/trainer/rloo_trainer.py sha256=dCyvhji93008sjsEP-7XSONdA-rO9OrnUPq8iG2JbDE 30818
trl/trainer/sft_config.py sha256=q4wSvVLyLaIf7lYKZtEIEwjyUh4jmjX0jEXNvpjaOls 4049
trl/trainer/sft_trainer.py sha256=ekODnL3Iq3ihaWJRCOx7ik5jfJTgEaIjnuHJWbf8aFw 24875
trl/trainer/utils.py sha256=eT_YZTU0ZqMTgWjAQyK9uYjLbTNK08NJMH73f4tD2zk 64038
trl/trainer/xpo_config.py sha256=ABrkFAUYAYSTxOscIVBiYKWH_QJ_UBlNH56ZjYLJeUY 1406
trl/trainer/xpo_trainer.py sha256=e1aDRiMNOrgNQaS_Qkmq1-dPCgHy29OQ_m3BPipGhyU 25660
trl/trainer/xxx.py sha256=cWKhXllSOaSFtjJhlkOD4lGQffCuui-MtxyKURUFukI 2390
trl-0.13.0.dist-info/LICENSE sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ 11357
trl-0.13.0.dist-info/METADATA sha256=V2AZWjPbmDFMw3CktajS73EtivzmoUMU_NI1cb8vP3c 11836
trl-0.13.0.dist-info/WHEEL sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U 91
trl-0.13.0.dist-info/entry_points.txt sha256=EiubuQrZSGOohRB4xVoiVAyWsPsOHPSVpbzSk8YB0x0 37
trl-0.13.0.dist-info/top_level.txt sha256=QU12VhjlpAtMnIJqiO2np3RkTB_Eozt1d-g8QDf5P4c 4
trl-0.13.0.dist-info/RECORD — —

top_level.txt

trl

entry_points.txt

[console_scripts]
trl = trl.cli:main