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 |
— |
— |