45 Commits

Author SHA1 Message Date
hiyouga
b1986a06b9 fix bug in latest gradio
Former-commit-id: 44a962862b4a74e50ef5786c8d5719faaa65f63f
2024-04-04 00:55:31 +08:00
hiyouga
b12176d818 simplify readme
Former-commit-id: 0da6ec2d516326fe9c7583ba71cd1778eb838178
2024-04-02 20:07:43 +08:00
hiyouga
117b67ea30 add moe aux loss control #3085
Former-commit-id: c9187ebc944e2de454ace3304b7d28eabb1b1a81
2024-04-02 14:26:31 +08:00
hiyouga
6198121923 support save args in webui #2807 #3046
some ideas are borrowed from @marko1616


Former-commit-id: b5a062aa2d4a37670007e8b3dae5b6f5b7ffb15c
2024-03-30 23:09:12 +08:00
hiyouga
9408366a36 fix #2982
Former-commit-id: e5e6a0c50c7a1c0052ed6b459450b9735ff2c9a1
2024-03-28 20:22:31 +08:00
hiyouga
92248f9cb2 fix #2936
Former-commit-id: 9ae646fbbd809057a9c54fe41e1ae5a07a674556
2024-03-24 00:43:21 +08:00
hiyouga
935ee0a023 support fsdp + qlora
Former-commit-id: b894bf8e84be689db258021f0638e9ac939abcbc
2024-03-21 00:36:06 +08:00
hiyouga
056d2d956a support vllm
Former-commit-id: 889f6e910e654d8ec3922c2185042d737ffbf1c3
2024-03-07 20:26:31 +08:00
hiyouga
73d9dfc7ab fix version checking
Former-commit-id: 5780da8d640609cca388f55983d0251e5547209a
2024-03-06 14:51:51 +08:00
hiyouga
596b6828cb support llama pro #2338 , add rslora
Former-commit-id: 40d659b7f30dd5a004703c176ec1f22dc864e505
2024-02-15 02:27:36 +08:00
hiyouga
66e0e651b9 format style
Former-commit-id: 53b683531b83cd1d19de97c6565f16c1eca6f5e1
2024-01-20 20:15:56 +08:00
hiyouga
a423274fd9 support function calling
Former-commit-id: 66533b3f65babf2429c92c0f8fafe4eff5e0ff63
2024-01-18 09:54:23 +08:00
hiyouga
73cab9d9d4 fix #2161
Former-commit-id: 9acd5a2b678cd07f8e3b48eca76c4cbacb559e37
2024-01-11 17:04:13 +08:00
hiyouga
64246d42d2 improve web ui
Former-commit-id: 5c0148c018b12b52bc5748acfd6ad43836f2edb5
2024-01-10 12:37:45 +08:00
hiyouga
a7ff095399 fix #2090
Former-commit-id: 13ec720990a88b01f7f5e2a99a87f95128dc3537
2024-01-04 23:05:08 +08:00
hiyouga
dba1af4841 add max_memory for gptq #1923
Former-commit-id: 9afc42c8b999fbbc206d9a467ca5795b27a10096
2023-12-20 18:15:17 +08:00
hiyouga
9f77e8b025 support autogptq in llama board #246
Former-commit-id: fea01226703d1534b5cf511bcb6a49e73bc86ce1
2023-12-16 16:31:30 +08:00
yhyu13
7d1fe50977 Use llmtuner logger
Former-commit-id: ef5a560b4246e04e0ef2612e3520e05288e93707
2023-12-16 07:15:27 +00:00
yhyu13
c0e5e3c5d5 Improve logging for unknown args
Former-commit-id: 03e49d76ca91f7fcaf1c013740d5f6bfc11a2028
2023-12-16 05:16:29 +00:00
hiyouga
fb4c5f3c91 fix #1715
Former-commit-id: 3f9192dbbbafdc2171d2eb80282d5cae47565b7b
2023-12-03 22:35:47 +08:00
hiyouga
4a14099cfd fix #1707 #1710
Former-commit-id: 243a596518ad69cf1eec20a082534b9e94353ce4
2023-12-03 11:33:12 +08:00
hiyouga
5f572cbd77 fix gptq training
Former-commit-id: bec58e3dc575aa4247e563881a456328ee5ef496
2023-12-02 00:27:15 +08:00
hiyouga
f1d7228a74 fix #1703
Former-commit-id: eee2e9abf6df345c5471e8ca7639293543ba720c
2023-12-01 22:55:41 +08:00
hiyouga
72bbd5bdef patch modelscope
Former-commit-id: 8888cf53f040f5a2d8c0e59cddf79b252449bf58
2023-12-01 22:53:15 +08:00
hiyouga
4738d002c7 tiny fix
Former-commit-id: 37aa7099dff2a9a7b52e259dac92de41ce606946
2023-12-01 15:58:50 +08:00
billvsme
7b45f5068f improve get_current_device
Former-commit-id: 2b07815e7fc8dc6ad0a7e9eccdd6681fbab35f3c
2023-11-30 22:40:35 +08:00
hiyouga
28258aecd2 update ppo trainer
Former-commit-id: caa525a5c6f228b9ad71387d1fe4f1c2ffa2479e
2023-11-20 21:39:15 +08:00
hiyouga
6889f044fb fix #1558
Former-commit-id: 263b2b24c8a649b51fa5ae768a24e67def8e0e96
2023-11-19 14:15:47 +08:00
hiyouga
7a3a0144a5 support full-parameter PPO
Former-commit-id: 4af967d69475e1c9fdf1a7983cd6b83bd431abff
2023-11-16 02:08:04 +08:00
hiyouga
09a4474e7f disentangle model from tuner and rename modules
Former-commit-id: 02cbf91e7e424f8379c1fed01b82a5f7a83b6947
2023-11-15 16:29:09 +08:00
hiyouga
64fc9ba678 refactor evaluation, upgrade trl to 074
Former-commit-id: ed09ebe2c1926ffdb0520b3866f7fd03a9aed046
2023-11-13 22:20:35 +08:00
hiyouga
3198a7e5f4 refactor model_dtype, fix PPO trainer
Former-commit-id: 3e17ee5afbcb823a7c9a2f91864b3750cd79edb4
2023-10-11 23:16:01 +08:00
hiyouga
7143c551ab support lora target auto find
Former-commit-id: bce9984733d88bf013847eed523d1c75fdf0995e
2023-09-09 15:38:37 +08:00
hiyouga
218f36bca5 add Baichuan2 models
Former-commit-id: 36960025e9274b574f57e7a7bf453cd96956e922
2023-09-06 18:36:04 +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
7f0b908de2 update webui
Former-commit-id: da30d0fb4abdb825f3383ddd106bb06a84695b7a
2023-08-14 22:45:26 +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
ca719a8697 support DPO training (2305.18290)
Former-commit-id: 6d98de148e4af63a7028dfaeb6cf86eb56a4488f
2023-08-11 03:02:53 +08:00
hiyouga
d6e922dc1c tiny fix
Former-commit-id: 81ef7017a4c96441951adeff0276cc5ab76a3544
2023-08-03 17:42:28 +08:00
hiyouga
2e19afedb8 support Qwen-7B, fix InternLM-7B inference
Former-commit-id: 25d2ca29ecb70cbfd5206333c667042a0c4d2e5a
2023-08-03 15:53:32 +08:00
hiyouga
250fecfcd4 Fix #294
Former-commit-id: 09762d9849655f5e6c71b9472d55b42489dd944b
2023-08-01 18:13:03 +08:00
hiyouga
dd3f3e9749 support streaming data, fix #284 #274 #268
Former-commit-id: 819cc1353599e5fa45658bc56dd0dbe4b258b197
2023-07-31 23:33:00 +08:00
hiyouga
fafec8b7a5 fix #268
Former-commit-id: 1eee0207fb370bb9e234e9bd3f9a0c47d7d01bc9
2023-07-28 17:02:26 +08:00
hiyouga
6261fb362a modity code structure
Former-commit-id: 0682ed357210897e0b67c4a6eb31a94b3eb929f1
2023-07-15 16:54:28 +08:00