134 Commits

Author SHA1 Message Date
hiyouga
5ee1bdecdc add MMLU and C-Eval script
Former-commit-id: 465ee8119aa489a41bee0b01b3c105a2f3dd137f
2023-09-23 00:34:17 +08:00
hiyouga
48e7b600a8 fix error info
Former-commit-id: 7e8655c8b59c3fdc455e304cf875a6b7fcb69290
2023-09-19 18:30:23 +08:00
hiyouga
4e86462bad fix #762 #814
Former-commit-id: d4be857e23c74ed65e06903e19da6f18f15d9e30
2023-09-12 16:10:10 +08:00
hiyouga
8ac7ec0b48 tiny fix
Former-commit-id: 3b306478d4ccbf037ae1acc122f6dca11c718731
2023-09-11 18:27:08 +08:00
hiyouga
33bab0e7c1 update flashattn, fix ppo save model
Former-commit-id: 0fbece85a70222e5262a2295203de07ffe648fda
2023-09-11 17:25:36 +08:00
hiyouga
6a71361a54 remove PeftTrainer
Former-commit-id: b218c271edfb07006ddc34b1aca404088de6c528
2023-09-10 22:23:23 +08:00
hiyouga
8ab5566dc0 support FlashAttention2
Former-commit-id: d8aa1404bee9842f3e4cd037ad8d66c85470ac37
2023-09-10 20:43:56 +08:00
hiyouga
f865d0bd51 fix lora target
Former-commit-id: a51b7c98acc599de5ed2eaeeebe7b184105722c5
2023-09-09 17:04:45 +08:00
hiyouga
c818a7ff60 support lora target auto find
Former-commit-id: bca1a247bcef51dced59655c8a14c197569367ca
2023-09-09 15:38:37 +08:00
hiyouga
9ed4bb63d4 change to right-padding, update reward score #803
Former-commit-id: 8ea32e4046d75ddfa9517669e9de9f48fea720c6
2023-09-08 20:04:31 +08:00
hiyouga
62941919e8 fix chatglm template
Former-commit-id: 8aaaa132d49b4c758256a6159270cea4351f946c
2023-09-08 14:45:58 +08:00
hiyouga
f74b980650 fix baichuan templates
Former-commit-id: 85b1f6632a752029dabdaed87c58986deb3a6b1d
2023-09-07 18:54:14 +08:00
hiyouga
51f662860d update baichuan2 template
Former-commit-id: 0531886e1f534217dc3c9c0775d29fcf77ff7f5f
2023-09-06 21:43:06 +08:00
hiyouga
f9aee17f9d add Baichuan2 models
Former-commit-id: 62ce65c6282d2bbcb765354acc2819cc3e983a46
2023-09-06 18:36:04 +08:00
hiyouga
a4fd976048 refactor dataset_attr, add eos in pt, fix #757
Former-commit-id: a9d1fb72f791ae57a4d12f4e3a7e2abccf6a7077
2023-09-01 19:00:45 +08:00
codemayq
ea74e5a81b update llama2 template
Former-commit-id: 0bcc489c42fc41b2c7ee51cced2dc995256a02d8
2023-08-30 16:23:56 +08:00
codemayq
4b29d9d2b0 add dataset stage and filter dataset when stage chosen in webui
Former-commit-id: c0e4d1e81b41c9a36291d8bee46d7d807c898c21
2023-08-23 18:54:23 +08:00
hiyouga
802494e20a update template
Former-commit-id: 4318347d3f1982c773dad1074636ec7b550770fd
2023-08-22 19:46:09 +08:00
hiyouga
e6f4eab4ab fix #608
Former-commit-id: 02d69b6fdefa6b303b84fb8195a159006fe3f50a
2023-08-21 17:49:36 +08:00
hiyouga
d3bef03dc6 fix baichuan template for training #597 #616
Former-commit-id: 0a3f6984259526775b0efdb8a1b0b24f564a7239
2023-08-21 17:41:51 +08:00
hiyouga
caf4a61e21 fix ChatGLM2 ppo #527 #528
Former-commit-id: 9f4c2adc9a9ca8e458d3868805e077182e0d336a
2023-08-18 00:34:59 +08:00
hiyouga
623a34b16f fix generation bug #532
Former-commit-id: be21fc83f9aed0af1e5a2f83f5d5eeb36f1d283c
2023-08-17 22:21:34 +08:00
hiyouga
3021a01b71 fix baichuan and intern template
Former-commit-id: 892fd39373b816cf079e0decc9cb57dfb5565242
2023-08-17 01:27:20 +08:00
hiyouga
edc15c62fa fix system prompt
Former-commit-id: 7407d9daa16bf6b3cd5002e16b2c53e402d2bc39
2023-08-16 01:35:52 +08:00
hiyouga
2ceaecfb42 fix baichuan template #481
Former-commit-id: 273135f59500a36cc30333ef2dd3689c6030e2ef
2023-08-15 11:38:21 +08:00
hiyouga
d15fe288df alert pad_token source
Former-commit-id: 80b4053602c02aec724ecf980f8a279ffdf9f975
2023-08-15 00:07:56 +08:00
hiyouga
02a61b08b1 update webui
Former-commit-id: 9d0f6214b68a653c0a67632437b227ab8f589bed
2023-08-14 22:45:26 +08:00
codemayq
ee7da14f81 add template match and stage in webui
Former-commit-id: 79c68e552722079faf2ab0858870b481844d66ae
2023-08-14 20:42:59 +08:00
hiyouga
3f0a2d6adc support rope scaling, fix #475 #476 #478
Former-commit-id: fa940c17b8d3e379af08804003f1a522c1cd6ac4
2023-08-12 20:46:27 +08:00
codemayq
3ba1b81105 add sft script preview in webui
Former-commit-id: 6bc8e9866d482c945dd98f4e9ab205a7d7270755
2023-08-12 13:53:55 +08:00
hiyouga
7bd4c59b7e fix unusual output of 8bit models #278 #391
Former-commit-id: dd51c242032ce3f878cb191dc144536db4a2bb45
2023-08-12 00:25:29 +08:00
hiyouga
79f4ba0d26 Release v0.1.6
Former-commit-id: a48cb0d474ef0648a97387daf5f623498b5e3ee6
2023-08-11 23:25:57 +08:00
hiyouga
21bf79e72b add defaults
Former-commit-id: d3844e97e387b2106a32a576a61318ecec948e23
2023-08-11 13:56:26 +08:00
hiyouga
eb26bfc2ba fix stop word in baichuan template
Former-commit-id: d59f9389590aab570f68ad4898b035741f9fd1c8
2023-08-11 13:51:46 +08:00
hiyouga
f1485ab927 fix baichuan template
Former-commit-id: 9c6dd1051417c91074daa7dd6ed6cc53448135ad
2023-08-11 13:45:47 +08:00
hiyouga
abdfa26d06 support DPO training (2305.18290)
Former-commit-id: 3ec4351cfdaf2aefcc7d13345e19d79874ed61d3
2023-08-11 03:02:53 +08:00
hiyouga
0dc9b41b16 fix template
Former-commit-id: eb6e571cb7c0a6da6696e8ce4b39cdcdb7f04e36
2023-08-09 23:14:27 +08:00
hiyouga
ce9ffca0d9 fix template
Former-commit-id: ac29f4d5f0d9d514aec9224fd751b9eb49430e7e
2023-08-09 23:10:20 +08:00
hiyouga
6404167ab7 support val set in streaming mode
Former-commit-id: d86ea314a197fd821770d895e988c48d46679047
2023-08-09 23:00:26 +08:00
hiyouga
d01c1231ed fix tokenizer
Former-commit-id: 572ea3bafb1b495e33b1abd1998972f3a5e6f310
2023-08-09 17:52:15 +08:00
hiyouga
28a807472b fix rm #420, fix template #426, fix #423
Former-commit-id: 39cd8b6989c9190d213e65467ec41f34ea04c5bc
2023-08-09 16:23:31 +08:00
hoshi-hiyouga
c3eb40b971 fix llama2 template
Former-commit-id: 2d90685358c938c1990e6a6fc4b7f98d183522de
2023-08-09 00:58:27 +08:00
hoshi-hiyouga
a37e1c11c9 fix tokenizer
Former-commit-id: 32fa5e8d706050a30a3eb49f9a6bc2591f9c21ea
2023-08-09 00:54:54 +08:00
hiyouga
4f714ba314 update webui
Former-commit-id: 3a720aac669708d17152d4e96c2018b5ccc27b75
2023-08-09 00:26:11 +08:00
hiyouga
77aa9853fb fix tokenizer #417
Former-commit-id: eecc4b2131e88b38fcd2659b52799a2f6459822f
2023-08-08 23:59:41 +08:00
hiyouga
70b53d9503 fix bug
Former-commit-id: 4b841a6b35585120c65e2718d6002c69cc40b925
2023-08-08 17:55:55 +08:00
hiyouga
c796c542c8 fix chatml template #408
Former-commit-id: a9980617f5c6e3356b672c8635696b2f2e308a5e
2023-08-08 17:44:39 +08:00
hiyouga
733b395822 update readme
Former-commit-id: 20cf27976f24db2667955a8007e0ce2baa35fc82
2023-08-07 15:02:02 +08:00
hiyouga
39955c28ff fix qwen tokenizer #361
Former-commit-id: 7f18d2a3359bcaab0f208f8c4a4bb13b6638072b
2023-08-05 17:06:05 +08:00
hiyouga
45af1a951f fix template for tiktoken
Former-commit-id: 1afa51c2fa9839056644803eedef4e9d1af0d51e
2023-08-05 13:42:42 +08:00