Commit Graph

407 Commits

Author SHA1 Message Date
hiyouga
daebca2368 tiny fix
Former-commit-id: c8b4c7fee5
2024-08-20 00:10:52 +08:00
hoshi-hiyouga
a7604a95c1 Merge pull request #5156 from YeQiuO/main
fix Llama-template's system prompt bug

Former-commit-id: 15be296347
2024-08-20 00:09:03 +08:00
hoshi-hiyouga
103132aa99 Update template.py
Former-commit-id: ec72eeca52
2024-08-20 00:03:33 +08:00
hoshi-hiyouga
033dd1f1dc Merge pull request #5163 from liu-zichen/fix_ppo_optim
fix lr not change

Former-commit-id: da335d42c3
2024-08-19 23:56:24 +08:00
hoshi-hiyouga
5e19a604a6 Merge pull request #5185 from chenhuiyu/feature/add-sailorllm-template
Add SailorLLM template

Former-commit-id: f59c9bef31
2024-08-19 23:51:49 +08:00
hoshi-hiyouga
5582674f06 Merge pull request #5188 from Zxilly/main
fix: report correct device count for intel xpu
Former-commit-id: d39f4a62d3
2024-08-19 23:51:39 +08:00
hoshi-hiyouga
a921505f59 Update template.py
Former-commit-id: 5f3300ec5d
2024-08-19 23:40:16 +08:00
Ricardo
a9312387bc _is_bf16_available judgment supports npu
Former-commit-id: 384ab8db84
2024-08-16 02:58:22 +00:00
Zxilly
41a8387195 fix: report correct device count for intel xpu
Former-commit-id: dc36fcc3de
2024-08-15 08:30:43 +00:00
Huiyu Chen
66a7f4f128 Add SailorLLM template
Former-commit-id: 2502833a77
2024-08-15 15:10:14 +08:00
liu-zichen
8a7ab8ab21 fix lr not change
Former-commit-id: ddee718b31
2024-08-13 16:33:34 +08:00
“Wzw”
3e159a0a83 fix Llama-template's system prompt bug
Former-commit-id: bcbbf45063
2024-08-12 19:22:12 +08:00
hiyouga
a8add5c04b add qwen2 math models
Former-commit-id: dc770efb14
2024-08-09 20:20:35 +08:00
hiyouga
5eacd17090 add adam_mini to readme
Former-commit-id: e2a28f51c6
2024-08-09 20:02:03 +08:00
hoshi-hiyouga
792da85866 Merge pull request #5095 from relic-yuexi/feat-optimizer
Feat optimizer

Former-commit-id: ef482394f0
2024-08-09 19:51:33 +08:00
hiyouga
b5146facff follow #5115
Former-commit-id: c87023d539
2024-08-09 18:03:00 +08:00
hoshi-hiyouga
397e4daa5d Merge pull request #5115 from YeQiuO/main
fix: `Train on the last turn only` truncate bug
Former-commit-id: 51542cb15f
2024-08-09 17:58:27 +08:00
hoshi-hiyouga
54f57fb354 Update template.py
Former-commit-id: 4f62e1cb24
2024-08-09 16:27:42 +08:00
“Wzw”
13e5fff97a mask_history args verify valid
Former-commit-id: 2fa1e0b2ad
2024-08-08 10:12:01 +08:00
“Wzw”
0bd25c3a6b fix mask_history tiny bug
Former-commit-id: b5ca86cc07
2024-08-08 10:09:33 +08:00
moontidef
44f7c4dd56 feat: add support for adammini
Former-commit-id: 82bc15dc79
2024-08-07 10:08:22 +08:00
moontidef
b0d32b2041 fix: rename optimzer to optimizer
Former-commit-id: 40908a36fa
2024-08-07 10:05:01 +08:00
moontidef
1cc927b536 Merge branch 'hiyouga:main' into main
Former-commit-id: 55f32dfbf9
2024-08-06 00:18:45 +08:00
moontidef
733cb9087b fix: fix the deepseekcoder template to avoid repeat problem
Former-commit-id: b82ecbedd0
2024-08-05 23:55:45 +08:00
hiyouga
20013e130b fix #5048
Former-commit-id: b7ca6c8dc1
2024-08-05 23:48:19 +08:00
codingma
7125b6cf70 support gemma-2-2b
Former-commit-id: dc09d454f2
2024-08-01 13:45:48 +08:00
hoshi-hiyouga
e678c1ccb2 Merge pull request #5010 from Eruly/main
Add Korean web UI (llamafactory-cli webui)

Former-commit-id: cd420c1938
2024-07-30 01:55:54 +08:00
eruly
ccc0825008 Add Korean web UI (llamafactory-cli webui)
Former-commit-id: 371009e522
2024-07-29 13:47:13 +00:00
codingma
8132725f2e fix pissa save
Former-commit-id: 2c1ca9f742
2024-07-29 10:44:34 +08:00
hoshi-hiyouga
0ac7824822 Merge pull request #4892 from piamo/main
update deepseek template

Former-commit-id: 8a2846cfe1
2024-07-26 11:49:34 +08:00
hoshi-hiyouga
29d9a9827a Merge pull request #4950 from liuwwang/main and fi
fix: Repair the issue where quantization failed after merging the adapter.
Former-commit-id: 9839c6d1f6
2024-07-26 11:48:56 +08:00
hiyouga
d984942c82 update webui
Former-commit-id: 30f8149d11
2024-07-24 21:11:51 +08:00
hiyouga
0aad78694a tiny fix
Former-commit-id: ace1d44857
2024-07-24 18:33:39 +08:00
hiyouga
d63beb7a24 fix #4928
Former-commit-id: 091010492b
2024-07-24 17:00:29 +08:00
hiyouga
91e54d458f add mistral nemo model
Former-commit-id: 1550fe7331
2024-07-24 16:25:53 +08:00
hiyouga
e0875f82b3 add llama3.1
Former-commit-id: 26533c0604
2024-07-24 16:20:11 +08:00
Liuww
ed05486b98 fix: Repair the issue where quantization failed after merging the adapter.
Former-commit-id: f91a9a250a
2024-07-24 14:31:29 +08:00
hiyouga
1cddf80a97 tiny fix
Former-commit-id: 5665062ca0
2024-07-22 21:10:15 +08:00
hoshi-hiyouga
37c6a0c6dc fix #4917
Former-commit-id: 26082fc6c9
2024-07-22 11:28:31 +08:00
hiyouga
dbe26e7cdf tiny fix
Former-commit-id: c333e2f49d
2024-07-22 00:06:03 +08:00
hiyouga
8d06679a3f fix flashattn + packing
Former-commit-id: 4135e69406
2024-07-21 17:07:45 +08:00
huangpan.foo
ee4c3f32d1 update deepseek template
Former-commit-id: 44e48e2b82
2024-07-19 15:02:54 +08:00
hiyouga
726e7046db set dev version
Former-commit-id: 88c7fc1599
2024-07-19 02:01:46 +08:00
hiyouga
542658c986 update parser
Former-commit-id: 8f6995081c
2024-07-19 01:36:39 +08:00
hiyouga
f5cfea56bd release v0.8.3
Former-commit-id: bbd5a64423
2024-07-19 01:21:18 +08:00
hiyouga
e1e01d7efd add unittest
Former-commit-id: 608de799a2
2024-07-19 01:06:27 +08:00
hiyouga
34f16cc635 follow #4878 fix #4684
Former-commit-id: 779aae83d2
2024-07-18 22:06:12 +08:00
Shiyu Zhang
249adacc4d 仅仅训练最后一轮对话
Former-commit-id: 1e7b396ff2
2024-07-18 15:30:25 +08:00
hiyouga
3c7b10b1fa fix metrics #4786
Former-commit-id: beec77a089
2024-07-17 00:47:00 +08:00
hiyouga
e90fae61f4 support batch_eval_metrics, fix #4826
Former-commit-id: d774b94f12
2024-07-17 00:33:00 +08:00