80 Commits

Author SHA1 Message Date
hiyouga
42e0b30476 update flashattn, fix ppo save model
Former-commit-id: 0b08bc3dac246d4aa3f89afb7172529dcad9c39f
2023-09-11 17:25:36 +08:00
hiyouga
a09a7b650d remove PeftTrainer
Former-commit-id: cc0cff3e991f194732d278e627648e528118a719
2023-09-10 22:23:23 +08:00
hiyouga
a402161631 support FlashAttention2
Former-commit-id: 23e56c5554b948d4f08ad87849b261eafd2c7890
2023-09-10 20:43:56 +08:00
hiyouga
f91c5f2638 fix lora target
Former-commit-id: d822e41e7ac7e310ee49e347fc45754284ce30b8
2023-09-09 17:04:45 +08:00
hiyouga
7143c551ab support lora target auto find
Former-commit-id: bce9984733d88bf013847eed523d1c75fdf0995e
2023-09-09 15:38:37 +08:00
hiyouga
612d97db6f change to right-padding, update reward score #803
Former-commit-id: baa90415bc8f5ebd423d001378b51c3a3a6c2ec7
2023-09-08 20:04:31 +08:00
hiyouga
bb1b67c076 fix chatglm template
Former-commit-id: 69a824628b4d6a56a680a7e713b217877c6c15c5
2023-09-08 14:45:58 +08:00
hiyouga
eae7b331d3 fix baichuan templates
Former-commit-id: f48a49e835b32f3991cfad8874c7b9c78953809f
2023-09-07 18:54:14 +08:00
hiyouga
ed89e29bcc update baichuan2 template
Former-commit-id: 16d9f8ba176443c5b397233da621600d6e1e1eec
2023-09-06 21:43:06 +08:00
hiyouga
218f36bca5 add Baichuan2 models
Former-commit-id: 36960025e9274b574f57e7a7bf453cd96956e922
2023-09-06 18:36:04 +08:00
hiyouga
e5b72c6a77 refactor dataset_attr, add eos in pt, fix #757
Former-commit-id: 0feec9a830b917b36686b61938a66e842eccf930
2023-09-01 19:00:45 +08:00
codemayq
9ae3fb4ced update llama2 template
Former-commit-id: 01de1d51d9fa5a22a338b6ed18ffad4d0ad5e3e8
2023-08-30 16:23:56 +08:00
codemayq
cbc7db3478 add dataset stage and filter dataset when stage chosen in webui
Former-commit-id: 26e4136449a4df6028d834fd16a0f4a7c532759d
2023-08-23 18:54:23 +08:00
hiyouga
6310613699 update template
Former-commit-id: a95f3a4d62de1073a78125401cf4289ec0523156
2023-08-22 19:46:09 +08:00
hiyouga
4d128acc17 fix #608
Former-commit-id: c02a6809124fcfd06628c49c95d419ec2d8cc8ef
2023-08-21 17:49:36 +08:00
hiyouga
516df9ecce fix baichuan template for training #597 #616
Former-commit-id: 6530c1d972301eac9ef058b3235618bb09833f15
2023-08-21 17:41:51 +08:00
hiyouga
04fa430c6c fix ChatGLM2 ppo #527 #528
Former-commit-id: 60d6ad64d7c9f6445b0df8de0153c3a311974198
2023-08-18 00:34:59 +08:00
hiyouga
fa1893b59c fix generation bug #532
Former-commit-id: c071121e67374e5f09798db57cfc8668617a36ae
2023-08-17 22:21:34 +08:00
hiyouga
ffa09a01d6 fix baichuan and intern template
Former-commit-id: e1fd18fa6ef1009f978aca5210a259251a0b19a6
2023-08-17 01:27:20 +08:00
hiyouga
baa709674f fix system prompt
Former-commit-id: 411e775aa939bdd154a3f1e92921ede90d989f18
2023-08-16 01:35:52 +08:00
hiyouga
ca9a494d0c fix baichuan template #481
Former-commit-id: 7608c6c25877d97ef26a1c209c4073c9c42f4535
2023-08-15 11:38:21 +08:00
hiyouga
ef2ca0a827 alert pad_token source
Former-commit-id: f26a84e0d927d2554890daf431a93652e18f4235
2023-08-15 00:07:56 +08:00
hiyouga
7f0b908de2 update webui
Former-commit-id: da30d0fb4abdb825f3383ddd106bb06a84695b7a
2023-08-14 22:45:26 +08:00
codemayq
9585699918 add template match and stage in webui
Former-commit-id: d6283e7f041f08f76d18350cb5f6a6c58ca80e92
2023-08-14 20:42:59 +08:00
hiyouga
fdfb644f0a support rope scaling, fix #475 #476 #478
Former-commit-id: 337d5f68b72230e545e7a94ca789187c7a2b7187
2023-08-12 20:46:27 +08:00
codemayq
8bf5a98815 add sft script preview in webui
Former-commit-id: 2b72649b404750226aa418b61ef5a6c9ac03938f
2023-08-12 13:53:55 +08:00
hiyouga
be566a15a5 fix unusual output of 8bit models #278 #391
Former-commit-id: 337ce5272b81f5561162beb08814b0e5abf23703
2023-08-12 00:25:29 +08:00
hiyouga
d5f1b99ac4 Release v0.1.6
Former-commit-id: 43c8b3c3c8bfb2e32d17fb3e8b194938e37d54bd
2023-08-11 23:25:57 +08:00
hiyouga
bc665bacc7 add defaults
Former-commit-id: 4636d3bbe6b984ca93e3a80ae5239f3ddda461bd
2023-08-11 13:56:26 +08:00
hiyouga
52bfcf4883 fix stop word in baichuan template
Former-commit-id: cba5ac9cfc81f11b97831998ea15def5e0b487c2
2023-08-11 13:51:46 +08:00
hiyouga
06df3d6fb6 fix baichuan template
Former-commit-id: b1681fe35346381cda613297f1cbb710f0a6daa6
2023-08-11 13:45:47 +08:00
hiyouga
ca719a8697 support DPO training (2305.18290)
Former-commit-id: 6d98de148e4af63a7028dfaeb6cf86eb56a4488f
2023-08-11 03:02:53 +08:00
hiyouga
5f0d0d6b9b fix template
Former-commit-id: e3967eb1cdd8d19e8afee9ba52e7eb7d6cd86129
2023-08-09 23:14:27 +08:00
hiyouga
76cb63e4f6 fix template
Former-commit-id: 907e8cd86fbd4cdfa26dad21ceaf6e01d8fe37e4
2023-08-09 23:10:20 +08:00
hiyouga
467d571206 support val set in streaming mode
Former-commit-id: faed15b58ed00b1e09bb091e7eee48f5ef7c508b
2023-08-09 23:00:26 +08:00
hiyouga
972bfa700a fix tokenizer
Former-commit-id: 7849587cd4e149291d08edef9a528a1bad796c7e
2023-08-09 17:52:15 +08:00
hiyouga
a3a7465f00 fix rm #420, fix template #426, fix #423
Former-commit-id: 70ea3caaa7a7695c77179cd1bb18707a80a373d7
2023-08-09 16:23:31 +08:00
hoshi-hiyouga
031a819257 fix llama2 template
Former-commit-id: 6c74f726d4e672f5a1a57df201c27c1f697384f0
2023-08-09 00:58:27 +08:00
hoshi-hiyouga
eb4b4e3c8c fix tokenizer
Former-commit-id: fa463ef279b596d5d53cc169831f51b42031fc05
2023-08-09 00:54:54 +08:00
hiyouga
d2e1fe9b1d update webui
Former-commit-id: 343a4cd82b07a40f96ba413d1d991419ff07a24a
2023-08-09 00:26:11 +08:00
hiyouga
6e27a9e39a fix tokenizer #417
Former-commit-id: 01aa678311bfd213a4b410a4e0ff09f48a0d40a1
2023-08-08 23:59:41 +08:00
hiyouga
a281cdeb89 fix bug
Former-commit-id: c13ce66021b21e015871b84489eeafa127a424a4
2023-08-08 17:55:55 +08:00
hiyouga
cda698a67f fix chatml template #408
Former-commit-id: 21e0cc3f44c35ae689b00b274391492f413725ac
2023-08-08 17:44:39 +08:00
hiyouga
34a2bddfcd update readme
Former-commit-id: 06bcbb901f69265632892a5fcbc956b8be1153da
2023-08-07 15:02:02 +08:00
hiyouga
a70d56864e fix qwen tokenizer #361
Former-commit-id: 78a2fa95c8ab669254a6c8fce8138c4395fb0a09
2023-08-05 17:06:05 +08:00
hiyouga
fdbb2c5378 fix template for tiktoken
Former-commit-id: 8328447f81eb5b90310df08cf2928c83ef6355fe
2023-08-05 13:42:42 +08:00
hiyouga
3c0aaf42af remove redundant code
Former-commit-id: dcec1717592107ba9d26eb2ac520309da19d1805
2023-08-05 00:27:27 +08:00
hiyouga
438e19160a fix template
Former-commit-id: b88200a88ea112e043dc44058606805c60e32844
2023-08-05 00:25:00 +08:00
hiyouga
f2b2ff6950 fix llama2 template
Former-commit-id: 08f37145e0bca5f1a8fd7bad01c64dc69b07361b
2023-08-05 00:07:54 +08:00
hiyouga
5f50944baf fix bos and eos token
Former-commit-id: ab386f4c0fb5eaac24264a5bbef4c03deeb92158
2023-08-04 23:55:57 +08:00