29 Commits

Author SHA1 Message Date
hiyouga
f0f9d253d8 support autogptq in llama board #246
Former-commit-id: 71389be37cb0f1a65db6e501e11ca14e615c1a24
2023-12-16 16:31:30 +08:00
yhyu13
cc91724507 Use llmtuner logger
Former-commit-id: fc70a92cb6e9c22bab9a0695f476ae80461c656f
2023-12-16 07:15:27 +00:00
yhyu13
362e3c913f Improve logging for unknown args
Former-commit-id: 26817143ff86a853c011be11678235bcc803ccce
2023-12-16 05:16:29 +00:00
hiyouga
cd2b0a024b fix #1715
Former-commit-id: c9b166615c882ea6df29a1b379654fdbc680d904
2023-12-03 22:35:47 +08:00
hiyouga
2279b1948e fix #1707 #1710
Former-commit-id: 03d05991f81b51826d3a4d9da214504e19a301bd
2023-12-03 11:33:12 +08:00
hiyouga
4cc08e00c7 fix gptq training
Former-commit-id: f57445c7a01b726160070c4ea29486702a650ed6
2023-12-02 00:27:15 +08:00
hiyouga
a388af4adc fix #1703
Former-commit-id: 662d9a3a4ec5ee408f5c9574c502e0af662fd821
2023-12-01 22:55:41 +08:00
hiyouga
c60e79c12e patch modelscope
Former-commit-id: bd42c229b01a0bf3ceadb8cee5ad49a060cc2d13
2023-12-01 22:53:15 +08:00
hiyouga
a44ba7a2b8 tiny fix
Former-commit-id: e597d3c084c8700e247bad6e26d2ee40fc3c316b
2023-12-01 15:58:50 +08:00
billvsme
e400f2e8ad improve get_current_device
Former-commit-id: 40dfcbc3d4571ce022b6aa39db581c8b88a75b8d
2023-11-30 22:40:35 +08:00
hiyouga
f06c4c8f7a update ppo trainer
Former-commit-id: 5021062493ed63ad1f6133cfb543e4e7f528d2cc
2023-11-20 21:39:15 +08:00
hiyouga
48d6d925f7 fix #1558
Former-commit-id: 1740131d63d32aefc0370441baf4716ddb5ebcfe
2023-11-19 14:15:47 +08:00
hiyouga
f441932bd1 support full-parameter PPO
Former-commit-id: ce783036001397a20b0b4c5da2fea6d0c03389d2
2023-11-16 02:08:04 +08:00
hiyouga
06a4820836 disentangle model from tuner and rename modules
Former-commit-id: 4736344eb1595ee023a50d49e8118f4eee46305f
2023-11-15 16:29:09 +08:00
hiyouga
125587b187 refactor evaluation, upgrade trl to 074
Former-commit-id: 442aefb925c4ff02b98aa30c49c2e01d04f6496a
2023-11-13 22:20:35 +08:00
hiyouga
c9d1cd108d refactor model_dtype, fix PPO trainer
Former-commit-id: 2818af0b0967d7695f27658acac0b7e2c2728e5d
2023-10-11 23:16:01 +08:00
hiyouga
c818a7ff60 support lora target auto find
Former-commit-id: bca1a247bcef51dced59655c8a14c197569367ca
2023-09-09 15:38:37 +08:00
hiyouga
f9aee17f9d add Baichuan2 models
Former-commit-id: 62ce65c6282d2bbcb765354acc2819cc3e983a46
2023-09-06 18:36:04 +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
02a61b08b1 update webui
Former-commit-id: 9d0f6214b68a653c0a67632437b227ab8f589bed
2023-08-14 22:45:26 +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
abdfa26d06 support DPO training (2305.18290)
Former-commit-id: 3ec4351cfdaf2aefcc7d13345e19d79874ed61d3
2023-08-11 03:02:53 +08:00
hiyouga
2d96ec9c3e tiny fix
Former-commit-id: ff98f1cba8d3be5b6a516b26a6019f867365110e
2023-08-03 17:42:28 +08:00
hiyouga
9c84c4ed5d support Qwen-7B, fix InternLM-7B inference
Former-commit-id: 87f8f830e20aa839e089559c1d038954742000ef
2023-08-03 15:53:32 +08:00
hiyouga
5c7337d6f3 Fix #294
Former-commit-id: e6a3894b99db81fc966a607c0a92dfb2b5f3585a
2023-08-01 18:13:03 +08:00
hiyouga
e80b75b560 support streaming data, fix #284 #274 #268
Former-commit-id: 0411a4b3e122e7907441bc7a64b004948741a620
2023-07-31 23:33:00 +08:00
hiyouga
3e3652f4e0 fix #268
Former-commit-id: 91dd17d8a6fcb0a154f29a2d1ff9f4266b720b9e
2023-07-28 17:02:26 +08:00
hiyouga
a696148d6b modity code structure
Former-commit-id: f75137661358f9070bc70c341dfa2cc5fd69cf94
2023-07-15 16:54:28 +08:00