shtec-rlhf

View on PyPIReverse Dependencies (0)

0.0.2.dev0 shtec_rlhf-0.0.2.dev0-py3-none-any.whl

Wheel Details

Project: shtec-rlhf
Version: 0.0.2.dev0
Filename: shtec_rlhf-0.0.2.dev0-py3-none-any.whl
Download: [link]
Size: 276258
MD5: cf8a68ecbcc730a6a4f19d51f2983cb9
SHA256: 906ba18359facccdab424463c96633ad28ffdfc6c33ff4c445f0678ec30348fd
Uploaded: 2024-04-19 03:10:51 +0000

dist-info

METADATA

Metadata-Version: 2.1
Name: shtec-rlhf
Version: 0.0.2.dev0
Summary: shtec-rlhf: Safe Reinforcement Learning from Human Feedback
Author: PKU-Alignment Team
Project-Url: Homepage, https://github.com/PKU-Alignment/shtec-rlhf
Project-Url: Repository, https://github.com/PKU-Alignment/shtec-rlhf
Project-Url: Documentation, https://shtec-rlhf.readthedocs.io
Project-Url: Bug Report, https://github.com/PKU-Alignment/shtec-rlhf
License: Apache License, Version 2.0
Keywords: Reinforcement Learning,Safe Reinforcement Learning,Reinforcement Learning from Human Feedback,Safe Reinforcement Learning from Human Feedback,Large Language Model,Language Model,RLHF,Safe RLHF,LLM
Classifier: Development Status :: 4 - Beta
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.8
Requires-Dist: torch (>=1.13)
Requires-Dist: transformers (>=4.37)
Requires-Dist: datasets
Requires-Dist: tokenizers (>=0.13.3)
Requires-Dist: accelerate
Requires-Dist: deepspeed
Requires-Dist: numpy
Requires-Dist: scipy
Requires-Dist: sentencepiece
Requires-Dist: wandb
Requires-Dist: tensorboard
Requires-Dist: optree
Requires-Dist: matplotlib
Requires-Dist: tqdm
Requires-Dist: rich
Requires-Dist: isort (>=5.11.0); extra == "lint"
Requires-Dist: black (>=23.1.0); extra == "lint"
Requires-Dist: pylint[spelling] (>=2.15.0); extra == "lint"
Requires-Dist: mypy (>=1.0); extra == "lint"
Requires-Dist: flake8; extra == "lint"
Requires-Dist: flake8-bugbear; extra == "lint"
Requires-Dist: flake8-comprehensions; extra == "lint"
Requires-Dist: flake8-docstrings; extra == "lint"
Requires-Dist: flake8-pyi; extra == "lint"
Requires-Dist: flake8-simplify; extra == "lint"
Requires-Dist: ruff; extra == "lint"
Requires-Dist: doc8; extra == "lint"
Requires-Dist: pydocstyle[toml]; extra == "lint"
Requires-Dist: pyenchant; extra == "lint"
Requires-Dist: pre-commit; extra == "lint"
Provides-Extra: lint
Description-Content-Type: text/markdown
[No description]

WHEEL

Wheel-Version: 1.0
Generator: bdist_wheel (0.38.4)
Root-Is-Purelib: true
Tag: py3-none-any

RECORD

Path Digest Size
safe_rlhf/__init__.py sha256=ashAg9-6xz3JkI2zvooT7nw_RhXrAsqjxFb_iXhmtXo 1004
safe_rlhf/logger.py sha256=ExuYdZljD3vi26qYG82NfcgMpAEXngU346kOIketM4E 7572
safe_rlhf/utils.py sha256=BmGsx9qBLDJxUVoIXoRrRihl5SO2oAAi3d2pIHf4Iso 9193
safe_rlhf/version.py sha256=Lz7cxpYxmZyIPoUH7g-OGadB7SVoLKiV2ps1Gzl-8eY 1438
safe_rlhf/algorithms/__init__.py sha256=pAAzBve76T2KHZUJ0jthUvFfI9dXT1zQeo1mFU4UgMY 591
safe_rlhf/algorithms/dpo/__init__.py sha256=AXB-igq8n_KzE8qqv1NAuLyqLqfgbxJtpj3jNAyUDuk 450
safe_rlhf/algorithms/dpo/__main__.py sha256=zblja6UGuONSFThf37FHfEb9PDiHG64shi59xraLCmM 475
safe_rlhf/algorithms/dpo/main.py sha256=w0wHmpvGBWritooKrAwXQnQGCAxxJW05ntxPvMrqBfw 9251
safe_rlhf/algorithms/dpo/trainer.py sha256=LQOID50DVPRFCAQc7qFh9j1JODm3OQZSEEdX9wWC_Vk 10049
safe_rlhf/algorithms/ppo/__init__.py sha256=czYq9fMxaNDGWRnexbKf-xancav83Oy-v6IcA3fdiVs 423
safe_rlhf/algorithms/ppo/__main__.py sha256=nSol5s-QaCRXd5aoK18RkPkKY3NHXRVFTScDJdhQuYo 484
safe_rlhf/algorithms/ppo/main.py sha256=3tNc3Kp44Yr1rYHgSBqk-8I7pNkCrzE33n_CaDSLXJA 13680
safe_rlhf/algorithms/ppo/trainer.py sha256=f6oLuozkvmrEvl0cmjg1cSum9Icd7SedIeWpHw2nyVs 9018
safe_rlhf/algorithms/ppo_lag/__init__.py sha256=hmDQkdpktt6FErnOG2HPOWgAq5cYuF3B3HAByC9UYk8 447
safe_rlhf/algorithms/ppo_lag/__main__.py sha256=xuYaFWnGFH690UNDN_nBT96NPnBhajbflTNdmznvSSE 502
safe_rlhf/algorithms/ppo_lag/main.py sha256=6ynrAAn-or2pVNXIfvuDqYw0vV5616CVDDxBHdU9huI 15369
safe_rlhf/algorithms/ppo_lag/trainer.py sha256=I-nY-philnF40iMwRiw1txioMi0kgVvxaaHMQHN1L-M 18526
safe_rlhf/algorithms/ppo_reward_shaping/__init__.py sha256=VLLeoqpcCX2DFf699i0C_N959pheZlLeYdf5nMu0L2o 488
safe_rlhf/algorithms/ppo_reward_shaping/__main__.py sha256=jZ6MAE6fzquMBxFDvlMaE-XCwKtToReNrhFTF6AT6GI 524
safe_rlhf/algorithms/ppo_reward_shaping/main.py sha256=NIgv158ECz3uPnyC8JuByZ8-rftlPQPUqvdZzaZT87w 14470
safe_rlhf/algorithms/ppo_reward_shaping/trainer.py sha256=eH-nUzUzsDL0fU1ASfgPpE9HWKOX1FCtzj4W35hQi4Y 11517
safe_rlhf/configs/__init__.py sha256=J85eCKB2MDmQ4SmL_9mWCyFdfk2-raj3G54jugnql_8 702
safe_rlhf/configs/constants.py sha256=q9JDfA0Pk5Jdy25NNuiLit8ehxBWR_1wTRFEFgORYjE 1233
safe_rlhf/configs/deepspeed_config.py sha256=1wy6URa6Mt0FGG2m50IjM7X1667-dT-Q6wR4XYNPw38 5026
safe_rlhf/configs/ds_eval_config_template.json sha256=ACWig0lsY2L_GFxssLwasV0lv0wtJjvFBk6y10JkICk 443
safe_rlhf/configs/ds_train_config_template.json sha256=OVtNwtzZ666CfNZbIB8WZzSrPCSB23f0uxAT5HSA9XI 872
safe_rlhf/configs/fsdp_config.json sha256=LxAyJZsiCiuDYJh_96KLBDslLs3iUwV-6zhkdfIYCzo 66
safe_rlhf/datasets/__init__.py sha256=fnhamM3BsQAze0RELe9OmnLBdOXC5yEyhMbRqBJaf0Q 2085
safe_rlhf/datasets/base.py sha256=Ns1q9dX8DKPytyrQajqXz7QxNupOerDtAZ2RQpzyr-c 15436
safe_rlhf/datasets/preference.py sha256=4qli6PTNPtdSM_0sCpxqU6p2mTcCI8scIN-dIicIXDM 3801
safe_rlhf/datasets/prompt_only.py sha256=wfwnoYaGZjiQadIkkeM-yxz93Mf0-UrnDl3VMCW52Xg 2648
safe_rlhf/datasets/safety_preference.py sha256=JKsoKIgqWNLUu9XixvBOdXfyIOm22HpkFr_EIm9sm0E 5352
safe_rlhf/datasets/supervised.py sha256=XdrOp9L8CF_ZqnoG1HNy3KUKR8h2ZRP-2MxkSg9ARgI 3925
safe_rlhf/datasets/utils.py sha256=GQqv9mBB6Bvf4ngXTTEf1c-6pPqsHoLGsVu-FkSXYjM 1674
safe_rlhf/datasets/raw/__init__.py sha256=NnY1prUSHejEuWlHCbEopCThL3puCzXS7Efpe9aXUfo 1228
safe_rlhf/datasets/raw/alpaca.py sha256=fgF5AvExM-knIWEo6ZFl_L9UnzlMG-buA5TK-ZlR0yA 1180
safe_rlhf/datasets/raw/firefly.py sha256=t4c6cBwRkQcCyQCYH2lHqjcMhYTn6RGivXt5z7xslkY 961
safe_rlhf/datasets/raw/hh_rlhf.py sha256=CgRUPO0f4mZNkXUduVzK5zchE-ArrPQk0ygNWgdAf2s 4428
safe_rlhf/datasets/raw/moss.py sha256=GZoaJBZlCRFGbMuNReuB7aHiOSKy7zLSKNzNMnt4avw 4205
safe_rlhf/datasets/raw/safe_rlhf.py sha256=stZlxjQo45twg7Lapu2vjLePH6vnLcrIVixDXwHvzRg 2581
safe_rlhf/evaluate/__init__.py sha256=tLw1LTI-xeP-Cg3c9xl6ohOdRJKDI0cNFpxfMCveCWo 306
safe_rlhf/evaluate/arena.py sha256=6T6qhSuS-S3rB_Cn7g6k8h1XoUG1ygwQbqilOpL3jHw 19517
safe_rlhf/evaluate/cost.py sha256=Tikz0w4B_V_cFz7sk5aVkJfZylR1qOA5qbBQGQngo6M 13384
safe_rlhf/evaluate/reward.py sha256=g_mhwz1yJpzCdTONc2gG4ps2X--SURNTTd7UKNBlpZ0 9655
safe_rlhf/evaluate/bigbench/__init__.py sha256=2rnHarTsJT6DaCCrvcYkwLgIbc4D0mufZfFuTHQAhD0 307
safe_rlhf/evaluate/bigbench/__main__.py sha256=xYDK4M9ZDsnthU27lpJYQpuX96CaHE9d_1ksYpSBM7w 420
safe_rlhf/evaluate/bigbench/eval.py sha256=dbrNTwlu_buI8bzqkarW15xW21RHXBpRNFfaxctgkEw 6463
safe_rlhf/evaluate/bigbench/model.py sha256=8lqv3ZVyI5-miQuy2Ek7-SVV3I5tdN0iA_b3zpvigAQ 6635
safe_rlhf/evaluate/gpt4/__init__.py sha256=2rnHarTsJT6DaCCrvcYkwLgIbc4D0mufZfFuTHQAhD0 307
safe_rlhf/evaluate/gpt4/__main__.py sha256=3qjeZ864leH6OfXxfoNHuVGVbKhPLPtD-73EBD7WSMQ 417
safe_rlhf/evaluate/gpt4/eval.py sha256=Z6W-pKkzY2ke9p0gVAnqJ5gyCHQwTEP1OV8wQntYt2U 5801
safe_rlhf/evaluate/gpt4/problem.json sha256=EbcJd9s49jhQDH3Yb3hqzspKHOl2iOzBvElHssbOcTI 13213
safe_rlhf/finetune/__init__.py sha256=MN7OMncWB3N_nyoWoypGy2XD_ARL_zJGMXzHGzcZmG0 452
safe_rlhf/finetune/__main__.py sha256=zwE5rKdUqarYBgE01UU2riM6qUkDSYb9w3sQDcDbpiU 475
safe_rlhf/finetune/deepspeed.py sha256=EX9dsKa0j1y0ZRGuc6Cu6ZrNwDEgSp0mm0JEWZrog9E 8849
safe_rlhf/finetune/huggingface.py sha256=xuYbcP6rFcKSnU7-fDkm_gAAtnP6sGcReiJ34OAbje8 2822
safe_rlhf/finetune/main.py sha256=JCxv11mQXb812YbNhUIatxg9x8RrSrEtnVb6G3Z2_zU 458
safe_rlhf/finetune/trainer.py sha256=EaPuUQ5e_i5CcoN6GFzUPB1J5qQy3pIB1wB7YHjRE7Q 2395
safe_rlhf/models/__init__.py sha256=jEDxFTbt7PmpOCvozIqsd3bf8D50PlfmuixDsq5k2Oc 584
safe_rlhf/models/normalizer.py sha256=ADBLpSR2TclBm_eXCVzCVIZrSF8us_DLTqnVcsVpVzg 6565
safe_rlhf/models/pretrained.py sha256=G9pHXmCqcr3gOlphWqhlW7UFXZFVuCinZF_Wdhj4f6c 7439
safe_rlhf/models/score_model/__init__.py sha256=EEx4eTswdo0Nul4l2Fp7csJmvSaPG_lbDR3OXKRqz3s 9326
safe_rlhf/models/score_model/bloom/__init__.py sha256=B12RVL6IhDV6oqasFOgqBhcMBwz1R6Y7exDgHt1GF58 385
safe_rlhf/models/score_model/bloom/modeling_bloom.py sha256=V_oHxEvud6UKdKsKrs-eA8ysQ9Us2a0InpxitrLNu0A 4143
safe_rlhf/models/score_model/gemma/__init__.py sha256=ulOdr10D0pFaPikgVUu9Lw2zlqyHHMW6glDYBt4labY 385
safe_rlhf/models/score_model/gemma/modeling_gemma.py sha256=MPXGeW21LoQnbfkPzLihrSRzEOlwtHH00n25Rl3CPbk 3651
safe_rlhf/models/score_model/gpt2/__init__.py sha256=HRBLyFWkibXrPRsQRhrNTAzRe8WsVcjr1pOtbObR3_c 382
safe_rlhf/models/score_model/gpt2/modeling_gpt2.py sha256=aYgf3MOmg5u0PVa788ms0cHAWO7bbp6UtIERoQbCUy8 6137
safe_rlhf/models/score_model/gpt_neo/__init__.py sha256=a1VtByl_KhZTJDv91lUKqb7gxnSm8tPw7tjpcfjzrzY 390
safe_rlhf/models/score_model/gpt_neo/modeling_gpt_neo.py sha256=qrMFoLr9H_Tf7CFzHJzMUgEgxVNwyzumeX65VNdZzTg 3919
safe_rlhf/models/score_model/gpt_neox/__init__.py sha256=7jYour0eEu2aMcw2GOyvk9uAYRcUe_PMOCVbYKn4Iyc 393
safe_rlhf/models/score_model/gpt_neox/modeling_gpt_neox.py sha256=2Lk7KcpFsx0DXQTR8EMRpP2D8y2IRfQ82TNCHdgpaZQ 3629
safe_rlhf/models/score_model/gptj/__init__.py sha256=TfAdTJtr3WZwHfdRwEoPRGUQicqYcYCDopnIwHWLFUA 382
safe_rlhf/models/score_model/gptj/modeling_gptj.py sha256=ZpmYV9kQACz9gU1grzd-T1nFQTxFwYeREEk6hlipmB8 5867
safe_rlhf/models/score_model/llama/__init__.py sha256=m605AhBbVMZfMst0RRY8vX1mx-oSiY7wno8iv153B5c 385
safe_rlhf/models/score_model/llama/modeling_llama.py sha256=8pV0gQ7vRXlJgc6n5sjvUj0MzmKn1ipO6lNO4MPHtuU 3651
safe_rlhf/models/score_model/mistral/__init__.py sha256=HyjBF13LQvbeqoUamAxzA3Z8adv-x8Z-1pVQBCzGJGI 391
safe_rlhf/models/score_model/mistral/modeling_mistral.py sha256=aupabHPjK8aOKtJbvJQ1lYxl2Vg9aKzH-Wg8YE3Ox2k 3361
safe_rlhf/models/score_model/opt/__init__.py sha256=lYo1hOT5G1pwfZWin62mpAiUYaD2o7N2G5HKEZhEJyg 71
safe_rlhf/models/score_model/opt/modeling_opt.py sha256=qPcb3d7o1NEa4Ez-MPygKEsysfcj39n73EJo2cuMuqo 3344
safe_rlhf/models/score_model/phi/__init__.py sha256=ZyGMdiZF6J8e6lZBfi7hmGlKh629zW3ZhE8it43C1VM 71
safe_rlhf/models/score_model/phi/modeling_phi.py sha256=9QZMZVVdTvwVG5lYrxZLzqJx6PByCQa0cOBjfqE4QXU 3325
safe_rlhf/models/score_model/qwen2/__init__.py sha256=jQnZGUb7G2Ts1dt_lbHdLaA1RnyEcI0VjVFlb_3ISsc 77
safe_rlhf/models/score_model/qwen2/modeling_qwen2.py sha256=NxK4tZoqaL0wO5XPNmWZxRRoCrPFeoFcpYaqLWOPxJ8 3537
safe_rlhf/serve/__init__.py sha256=2rnHarTsJT6DaCCrvcYkwLgIbc4D0mufZfFuTHQAhD0 307
safe_rlhf/serve/arena.py sha256=Q6weLBf3JZ5cC4sZDnh0goa3et5BMi4jFPUAG_FfUzM 2803
safe_rlhf/serve/chatbot.py sha256=o6iCKyWpOnR1mHmnz0K9WBtmM37hzzV9RDQCcSY2clM 11809
safe_rlhf/serve/cli.py sha256=rPJyYTOIZgPs9PMz72gzLrlds6HiGNafrvJeEsCOXSA 8659
safe_rlhf/trainers/__init__.py sha256=TvkW63UueR9_-QX5Pp-2xFHSRYVrx4Z-R_JgSIHnVko 262
safe_rlhf/trainers/base.py sha256=uri4sM66-JOL6fJR4wXRWOAkPa6iiVz1KkcT1w4Omt8 4348
safe_rlhf/trainers/rl_trainer.py sha256=gMM5LUqAJ4iZjCuIaFkgYiqvlb7Xwr2gQUMHQL88br4 25698
safe_rlhf/trainers/supervised_trainer.py sha256=M4LWMCiAROENK3F28-TgPRVnmyHVcLKbfs5o5gA4W4Y 8535
safe_rlhf/values/__init__.py sha256=GVFTSbyLOykQIE9cuvGNXOygcvAMfXVPOBl0sBvSb1s 178
safe_rlhf/values/cost/__init__.py sha256=_jy3qP81oqIdJ4gl7bT7MtFbsEs7pqnpT4IW3dA_wdw 83
safe_rlhf/values/cost/__main__.py sha256=JE9Cujsvm3LVs8uWOWX-NDi5_J0qlv_Qcuta8v07JSA 175
safe_rlhf/values/cost/main.py sha256=255Ni7zRgUg9lehdeuhAnq0LQBsmDcmWLiIcZe7dRBo 9732
safe_rlhf/values/cost/trainer.py sha256=jxmPCj6KHJPvydli4Q2EvzhneP-GTERHlwhxgsD7L4I 13712
safe_rlhf/values/reward/__init__.py sha256=7IJUgL0Q4HSUu22Nu9l2mNrIlFMCy71m02LAS2pyNP0 397
safe_rlhf/values/reward/__main__.py sha256=WZ8iDtEPAULo6TG8ELX22h-KTqX2oZCS8cTh4OO2z60 486
safe_rlhf/values/reward/main.py sha256=sQi2S7pSBv-626bbqUw5O-fL48h_e15Z1QSz5CfYfGg 9752
safe_rlhf/values/reward/trainer.py sha256=0lzmzeK3cBj-pIhlplpIQBYNbRuyK6_ZU9w-NFKdnkY 10744
shtec_rlhf/__init__.py sha256=fSE57cT2i7wss452UVTCGTnFEz42M-vYAM_HLFyZ00c 1005
shtec_rlhf/logger.py sha256=ExuYdZljD3vi26qYG82NfcgMpAEXngU346kOIketM4E 7572
shtec_rlhf/utils.py sha256=BmGsx9qBLDJxUVoIXoRrRihl5SO2oAAi3d2pIHf4Iso 9193
shtec_rlhf/version.py sha256=nRJCcbuPcpQZlJuW83URQ5smjkMqT2o8DW7ffw-RrlU 1439
shtec_rlhf/algorithms/__init__.py sha256=pAAzBve76T2KHZUJ0jthUvFfI9dXT1zQeo1mFU4UgMY 591
shtec_rlhf/algorithms/dpo/__init__.py sha256=AXB-igq8n_KzE8qqv1NAuLyqLqfgbxJtpj3jNAyUDuk 450
shtec_rlhf/algorithms/dpo/__main__.py sha256=zblja6UGuONSFThf37FHfEb9PDiHG64shi59xraLCmM 475
shtec_rlhf/algorithms/dpo/main.py sha256=w0wHmpvGBWritooKrAwXQnQGCAxxJW05ntxPvMrqBfw 9251
shtec_rlhf/algorithms/dpo/trainer.py sha256=LQOID50DVPRFCAQc7qFh9j1JODm3OQZSEEdX9wWC_Vk 10049
shtec_rlhf/algorithms/ppo/__init__.py sha256=czYq9fMxaNDGWRnexbKf-xancav83Oy-v6IcA3fdiVs 423
shtec_rlhf/algorithms/ppo/__main__.py sha256=nSol5s-QaCRXd5aoK18RkPkKY3NHXRVFTScDJdhQuYo 484
shtec_rlhf/algorithms/ppo/main.py sha256=3tNc3Kp44Yr1rYHgSBqk-8I7pNkCrzE33n_CaDSLXJA 13680
shtec_rlhf/algorithms/ppo/trainer.py sha256=f6oLuozkvmrEvl0cmjg1cSum9Icd7SedIeWpHw2nyVs 9018
shtec_rlhf/algorithms/ppo_lag/__init__.py sha256=sFteSqVoOK6FuQd5PGnV11joRLZndSgwYFbBpFCwC8A 448
shtec_rlhf/algorithms/ppo_lag/__main__.py sha256=P79CXfTKPLZpQnWIhDx5lw7A8OTxpdsPZNd1dmKOFxs 503
shtec_rlhf/algorithms/ppo_lag/main.py sha256=-iEvuCIS3lxTmPh4t1nZQwUJTTLf_4cozj1M-fKPEtY 15371
shtec_rlhf/algorithms/ppo_lag/trainer.py sha256=I-nY-philnF40iMwRiw1txioMi0kgVvxaaHMQHN1L-M 18526
shtec_rlhf/algorithms/ppo_reward_shaping/__init__.py sha256=c8ZK5V6q53JbS8RLZYvhoSCnoJ0NfpCR6MDwKZf-9ck 489
shtec_rlhf/algorithms/ppo_reward_shaping/__main__.py sha256=3QTcSOWQJ1W8Iw7KUCw59S5pkq13DSpcGJM87V6tmJI 525
shtec_rlhf/algorithms/ppo_reward_shaping/main.py sha256=pplDWgg2uKk1XxJvqVNQuga3WgRmG0n8NAKaXa9Dsko 14472
shtec_rlhf/algorithms/ppo_reward_shaping/trainer.py sha256=eH-nUzUzsDL0fU1ASfgPpE9HWKOX1FCtzj4W35hQi4Y 11517
shtec_rlhf/configs/__init__.py sha256=J85eCKB2MDmQ4SmL_9mWCyFdfk2-raj3G54jugnql_8 702
shtec_rlhf/configs/constants.py sha256=q9JDfA0Pk5Jdy25NNuiLit8ehxBWR_1wTRFEFgORYjE 1233
shtec_rlhf/configs/deepspeed_config.py sha256=1wy6URa6Mt0FGG2m50IjM7X1667-dT-Q6wR4XYNPw38 5026
shtec_rlhf/configs/ds_eval_config_template.json sha256=ACWig0lsY2L_GFxssLwasV0lv0wtJjvFBk6y10JkICk 443
shtec_rlhf/configs/ds_train_config_template.json sha256=OVtNwtzZ666CfNZbIB8WZzSrPCSB23f0uxAT5HSA9XI 872
shtec_rlhf/configs/fsdp_config.json sha256=LxAyJZsiCiuDYJh_96KLBDslLs3iUwV-6zhkdfIYCzo 66
shtec_rlhf/datasets/__init__.py sha256=fnhamM3BsQAze0RELe9OmnLBdOXC5yEyhMbRqBJaf0Q 2085
shtec_rlhf/datasets/base.py sha256=Ns1q9dX8DKPytyrQajqXz7QxNupOerDtAZ2RQpzyr-c 15436
shtec_rlhf/datasets/preference.py sha256=4qli6PTNPtdSM_0sCpxqU6p2mTcCI8scIN-dIicIXDM 3801
shtec_rlhf/datasets/prompt_only.py sha256=wfwnoYaGZjiQadIkkeM-yxz93Mf0-UrnDl3VMCW52Xg 2648
shtec_rlhf/datasets/safety_preference.py sha256=JKsoKIgqWNLUu9XixvBOdXfyIOm22HpkFr_EIm9sm0E 5352
shtec_rlhf/datasets/supervised.py sha256=XdrOp9L8CF_ZqnoG1HNy3KUKR8h2ZRP-2MxkSg9ARgI 3925
shtec_rlhf/datasets/utils.py sha256=GQqv9mBB6Bvf4ngXTTEf1c-6pPqsHoLGsVu-FkSXYjM 1674
shtec_rlhf/datasets/raw/__init__.py sha256=NnY1prUSHejEuWlHCbEopCThL3puCzXS7Efpe9aXUfo 1228
shtec_rlhf/datasets/raw/alpaca.py sha256=fgF5AvExM-knIWEo6ZFl_L9UnzlMG-buA5TK-ZlR0yA 1180
shtec_rlhf/datasets/raw/firefly.py sha256=t4c6cBwRkQcCyQCYH2lHqjcMhYTn6RGivXt5z7xslkY 961
shtec_rlhf/datasets/raw/hh_rlhf.py sha256=CgRUPO0f4mZNkXUduVzK5zchE-ArrPQk0ygNWgdAf2s 4428
shtec_rlhf/datasets/raw/moss.py sha256=GZoaJBZlCRFGbMuNReuB7aHiOSKy7zLSKNzNMnt4avw 4205
shtec_rlhf/datasets/raw/safe_rlhf.py sha256=jrk7GhABBVNtzVgNB1ARlbJ9fh_tR4cxd-tq5HKbrLQ 2582
shtec_rlhf/datasets/raw/shtec_rlhf.py sha256=jrk7GhABBVNtzVgNB1ARlbJ9fh_tR4cxd-tq5HKbrLQ 2582
shtec_rlhf/evaluate/__init__.py sha256=tLw1LTI-xeP-Cg3c9xl6ohOdRJKDI0cNFpxfMCveCWo 306
shtec_rlhf/evaluate/arena.py sha256=6T6qhSuS-S3rB_Cn7g6k8h1XoUG1ygwQbqilOpL3jHw 19517
shtec_rlhf/evaluate/cost.py sha256=fCqXyBlqcweVy8uENh3c29DQs5sqoe_xQEqpbNrkP6o 13385
shtec_rlhf/evaluate/reward.py sha256=vpDFS1kncgoFGO0PfARPyFZshFOc8ydzs80bOWlxGv4 9656
shtec_rlhf/evaluate/bigbench/__init__.py sha256=2rnHarTsJT6DaCCrvcYkwLgIbc4D0mufZfFuTHQAhD0 307
shtec_rlhf/evaluate/bigbench/__main__.py sha256=xYDK4M9ZDsnthU27lpJYQpuX96CaHE9d_1ksYpSBM7w 420
shtec_rlhf/evaluate/bigbench/eval.py sha256=dbrNTwlu_buI8bzqkarW15xW21RHXBpRNFfaxctgkEw 6463
shtec_rlhf/evaluate/bigbench/model.py sha256=8lqv3ZVyI5-miQuy2Ek7-SVV3I5tdN0iA_b3zpvigAQ 6635
shtec_rlhf/evaluate/gpt4/__init__.py sha256=2rnHarTsJT6DaCCrvcYkwLgIbc4D0mufZfFuTHQAhD0 307
shtec_rlhf/evaluate/gpt4/__main__.py sha256=3qjeZ864leH6OfXxfoNHuVGVbKhPLPtD-73EBD7WSMQ 417
shtec_rlhf/evaluate/gpt4/eval.py sha256=Z6W-pKkzY2ke9p0gVAnqJ5gyCHQwTEP1OV8wQntYt2U 5801
shtec_rlhf/evaluate/gpt4/problem.json sha256=EbcJd9s49jhQDH3Yb3hqzspKHOl2iOzBvElHssbOcTI 13213
shtec_rlhf/finetune/__init__.py sha256=MN7OMncWB3N_nyoWoypGy2XD_ARL_zJGMXzHGzcZmG0 452
shtec_rlhf/finetune/__main__.py sha256=zwE5rKdUqarYBgE01UU2riM6qUkDSYb9w3sQDcDbpiU 475
shtec_rlhf/finetune/deepspeed.py sha256=EX9dsKa0j1y0ZRGuc6Cu6ZrNwDEgSp0mm0JEWZrog9E 8849
shtec_rlhf/finetune/huggingface.py sha256=xuYbcP6rFcKSnU7-fDkm_gAAtnP6sGcReiJ34OAbje8 2822
shtec_rlhf/finetune/main.py sha256=JCxv11mQXb812YbNhUIatxg9x8RrSrEtnVb6G3Z2_zU 458
shtec_rlhf/finetune/trainer.py sha256=EaPuUQ5e_i5CcoN6GFzUPB1J5qQy3pIB1wB7YHjRE7Q 2395
shtec_rlhf/models/__init__.py sha256=jEDxFTbt7PmpOCvozIqsd3bf8D50PlfmuixDsq5k2Oc 584
shtec_rlhf/models/normalizer.py sha256=ADBLpSR2TclBm_eXCVzCVIZrSF8us_DLTqnVcsVpVzg 6565
shtec_rlhf/models/pretrained.py sha256=G9pHXmCqcr3gOlphWqhlW7UFXZFVuCinZF_Wdhj4f6c 7439
shtec_rlhf/models/score_model/__init__.py sha256=EEx4eTswdo0Nul4l2Fp7csJmvSaPG_lbDR3OXKRqz3s 9326
shtec_rlhf/models/score_model/bloom/__init__.py sha256=B12RVL6IhDV6oqasFOgqBhcMBwz1R6Y7exDgHt1GF58 385
shtec_rlhf/models/score_model/bloom/modeling_bloom.py sha256=V_oHxEvud6UKdKsKrs-eA8ysQ9Us2a0InpxitrLNu0A 4143
shtec_rlhf/models/score_model/gemma/__init__.py sha256=ulOdr10D0pFaPikgVUu9Lw2zlqyHHMW6glDYBt4labY 385
shtec_rlhf/models/score_model/gemma/modeling_gemma.py sha256=MPXGeW21LoQnbfkPzLihrSRzEOlwtHH00n25Rl3CPbk 3651
shtec_rlhf/models/score_model/gpt2/__init__.py sha256=HRBLyFWkibXrPRsQRhrNTAzRe8WsVcjr1pOtbObR3_c 382
shtec_rlhf/models/score_model/gpt2/modeling_gpt2.py sha256=aYgf3MOmg5u0PVa788ms0cHAWO7bbp6UtIERoQbCUy8 6137
shtec_rlhf/models/score_model/gpt_neo/__init__.py sha256=a1VtByl_KhZTJDv91lUKqb7gxnSm8tPw7tjpcfjzrzY 390
shtec_rlhf/models/score_model/gpt_neo/modeling_gpt_neo.py sha256=qrMFoLr9H_Tf7CFzHJzMUgEgxVNwyzumeX65VNdZzTg 3919
shtec_rlhf/models/score_model/gpt_neox/__init__.py sha256=7jYour0eEu2aMcw2GOyvk9uAYRcUe_PMOCVbYKn4Iyc 393
shtec_rlhf/models/score_model/gpt_neox/modeling_gpt_neox.py sha256=2Lk7KcpFsx0DXQTR8EMRpP2D8y2IRfQ82TNCHdgpaZQ 3629
shtec_rlhf/models/score_model/gptj/__init__.py sha256=TfAdTJtr3WZwHfdRwEoPRGUQicqYcYCDopnIwHWLFUA 382
shtec_rlhf/models/score_model/gptj/modeling_gptj.py sha256=ZpmYV9kQACz9gU1grzd-T1nFQTxFwYeREEk6hlipmB8 5867
shtec_rlhf/models/score_model/llama/__init__.py sha256=m605AhBbVMZfMst0RRY8vX1mx-oSiY7wno8iv153B5c 385
shtec_rlhf/models/score_model/llama/modeling_llama.py sha256=8pV0gQ7vRXlJgc6n5sjvUj0MzmKn1ipO6lNO4MPHtuU 3651
shtec_rlhf/models/score_model/mistral/__init__.py sha256=HyjBF13LQvbeqoUamAxzA3Z8adv-x8Z-1pVQBCzGJGI 391
shtec_rlhf/models/score_model/mistral/modeling_mistral.py sha256=aupabHPjK8aOKtJbvJQ1lYxl2Vg9aKzH-Wg8YE3Ox2k 3361
shtec_rlhf/models/score_model/opt/__init__.py sha256=lYo1hOT5G1pwfZWin62mpAiUYaD2o7N2G5HKEZhEJyg 71
shtec_rlhf/models/score_model/opt/modeling_opt.py sha256=qPcb3d7o1NEa4Ez-MPygKEsysfcj39n73EJo2cuMuqo 3344
shtec_rlhf/models/score_model/phi/__init__.py sha256=ZyGMdiZF6J8e6lZBfi7hmGlKh629zW3ZhE8it43C1VM 71
shtec_rlhf/models/score_model/phi/modeling_phi.py sha256=9QZMZVVdTvwVG5lYrxZLzqJx6PByCQa0cOBjfqE4QXU 3325
shtec_rlhf/models/score_model/qwen2/__init__.py sha256=jQnZGUb7G2Ts1dt_lbHdLaA1RnyEcI0VjVFlb_3ISsc 77
shtec_rlhf/models/score_model/qwen2/modeling_qwen2.py sha256=NxK4tZoqaL0wO5XPNmWZxRRoCrPFeoFcpYaqLWOPxJ8 3537
shtec_rlhf/serve/__init__.py sha256=2rnHarTsJT6DaCCrvcYkwLgIbc4D0mufZfFuTHQAhD0 307
shtec_rlhf/serve/arena.py sha256=Q6weLBf3JZ5cC4sZDnh0goa3et5BMi4jFPUAG_FfUzM 2803
shtec_rlhf/serve/chatbot.py sha256=o6iCKyWpOnR1mHmnz0K9WBtmM37hzzV9RDQCcSY2clM 11809
shtec_rlhf/serve/cli.py sha256=rPJyYTOIZgPs9PMz72gzLrlds6HiGNafrvJeEsCOXSA 8659
shtec_rlhf/trainers/__init__.py sha256=TvkW63UueR9_-QX5Pp-2xFHSRYVrx4Z-R_JgSIHnVko 262
shtec_rlhf/trainers/base.py sha256=AOn3tZWsXjjSnGppeE4u0CwD87BFqlMNwg9_feP3oKs 4349
shtec_rlhf/trainers/rl_trainer.py sha256=gMM5LUqAJ4iZjCuIaFkgYiqvlb7Xwr2gQUMHQL88br4 25698
shtec_rlhf/trainers/supervised_trainer.py sha256=M4LWMCiAROENK3F28-TgPRVnmyHVcLKbfs5o5gA4W4Y 8535
shtec_rlhf/values/__init__.py sha256=F8pKdnrsLOlY9cBDHxpkegRnQuGkz7WkB8DV6eelmIk 179
shtec_rlhf/values/cost/__init__.py sha256=_jy3qP81oqIdJ4gl7bT7MtFbsEs7pqnpT4IW3dA_wdw 83
shtec_rlhf/values/cost/__main__.py sha256=VYZLFxVDAWdeqcgG6TWqgNYPgWEWMPpX1bmar3IWqAM 176
shtec_rlhf/values/cost/main.py sha256=Nu8wMGNTaUrXfXwih5C5h8QuQ9WzXUBJUx5sDJ0pxiI 9733
shtec_rlhf/values/cost/trainer.py sha256=jxmPCj6KHJPvydli4Q2EvzhneP-GTERHlwhxgsD7L4I 13712
shtec_rlhf/values/reward/__init__.py sha256=7IJUgL0Q4HSUu22Nu9l2mNrIlFMCy71m02LAS2pyNP0 397
shtec_rlhf/values/reward/__main__.py sha256=oJIUK_JVk-r2lCwTkZJhsh9_Pr3s_POEAo1qZC2g1po 487
shtec_rlhf/values/reward/main.py sha256=K9RwLMHctUnI_lwo02SehkINfydyY-cDp8T9gZuauG4 9753
shtec_rlhf/values/reward/trainer.py sha256=0lzmzeK3cBj-pIhlplpIQBYNbRuyK6_ZU9w-NFKdnkY 10744
shtec_rlhf-0.0.2.dev0.dist-info/METADATA sha256=kj8ua6SXt_S-7pmWycUaVDhXl0sMeZ03r64rcv0W5tI 2394
shtec_rlhf-0.0.2.dev0.dist-info/WHEEL sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo 92
shtec_rlhf-0.0.2.dev0.dist-info/top_level.txt sha256=2HJwowMnZse7nGlMq36TDAFJT8pat6ikEOmBDkHgKBI 11
shtec_rlhf-0.0.2.dev0.dist-info/RECORD

top_level.txt

shtec_rlhf