Commit Graph

1620 Commits

Author SHA1 Message Date
hiyouga
5ef58eb655 fix #5334
Former-commit-id: 59d2b31e96
2024-09-03 19:09:42 +08:00
hiyouga
f837ae8cb5 fix #5338
Former-commit-id: 69d0acacc3
2024-09-03 17:45:17 +08:00
hiyouga
982585e375 lint
Former-commit-id: 22959bcdd3
2024-09-03 00:46:25 +08:00
hiyouga
6e98872622 fix #5324
Former-commit-id: a61c8c4890
2024-09-02 23:56:21 +08:00
naem1023
46695e42cc feat: add batch size of map function in the preprocessed dataset
Former-commit-id: 209313eeea
2024-09-02 13:52:47 +09:00
hoshi-hiyouga
5af92971bc fix trainer predict
Former-commit-id: 99fd9637bd
2024-09-02 10:15:29 +08:00
hoshi-hiyouga
5c9972a2d5 remove .cpu()
Former-commit-id: a6c6750e8a
2024-09-02 10:10:53 +08:00
hiyouga
b2a5f49a24 fix mm inference
Former-commit-id: 60fc6b926e
2024-09-02 01:47:40 +08:00
hiyouga
f13e974930 tiny fix
Former-commit-id: 3a6f19f017
2024-09-02 01:33:22 +08:00
hiyouga
859823eb23 add image num check
Former-commit-id: ce8c5a2647
2024-09-02 01:31:36 +08:00
hiyouga
bfdcc6bacf add rlhf-v dataset
Former-commit-id: 8e49940746
2024-09-01 22:57:41 +08:00
hiyouga
236f97b35c tiny fix
Former-commit-id: 55027282cd
2024-09-01 21:15:44 +08:00
hiyouga
413a206652 fix bug
Former-commit-id: 64cb947c60
2024-09-01 21:07:49 +08:00
hiyouga
cb776752f6 fix mixed mm inputs and rlhf-v
Former-commit-id: 9967ccb3ae
2024-09-01 20:52:47 +08:00
hiyouga
34dc36462c fix ci (temp)
Former-commit-id: b5063b4144
2024-08-31 02:03:56 +08:00
hiyouga
09a2ecebc4 add test mm plugin
Former-commit-id: a2a8c0b92c
2024-08-31 01:53:38 +08:00
hiyouga
f31e7e0dfc remove visual_inputs, fix qlora
Former-commit-id: a025c3df61
2024-08-31 00:24:51 +08:00
hiyouga
51a0016873 optimize predict vram
Former-commit-id: a244f143f4
2024-08-30 23:08:45 +08:00
hiyouga
92c398166d tiny fix
Former-commit-id: bee1bd43b9
2024-08-30 03:21:50 +08:00
hiyouga
913ee05e74 fix #5307
Former-commit-id: 8b588c7224
2024-08-30 02:45:40 +08:00
hiyouga
a83756b5e9 refactor mm training
Former-commit-id: 3382317e32
2024-08-30 02:14:31 +08:00
hoshi-hiyouga
98b0c7530c Merge pull request #5290 from simonJJJ/qwen2_vl
support qwen2-vl

Former-commit-id: 727e184840
2024-08-30 02:10:36 +08:00
hoshi-hiyouga
5730243179 fix bug
Former-commit-id: a8f22d8895
2024-08-30 02:05:26 +08:00
hiyouga
0e4ee9d9a3 update liger kernel
Former-commit-id: a7dd7d325e
2024-08-29 20:46:08 +08:00
hiyouga
f153ee13be fix #5292
Former-commit-id: aa1afdc756
2024-08-29 20:37:47 +08:00
hiyouga
21d3976eea fix #5295
Former-commit-id: ad72f3e065
2024-08-29 20:30:18 +08:00
hiyouga
1494fa1f18 fix #5305
Former-commit-id: 364b757e30
2024-08-29 20:16:01 +08:00
simonJJJ
d9fd8f26cc update
Former-commit-id: 734e019cc1
2024-08-28 20:22:46 +08:00
simonJJJ
8a09b1e732 initial-commit
Former-commit-id: aeb85f200b
2024-08-28 16:51:35 +08:00
hiyouga
7b5834b2dd tiny fix
Former-commit-id: f6ae4e75dd
2024-08-27 12:49:32 +08:00
hoshi-hiyouga
7cbfd64289 Merge pull request #5237 from marko1616/patch-1
Fix mllm api

Former-commit-id: dbe886ae5c
2024-08-27 12:24:43 +08:00
marko1616
388c3e4e47 ruff pass.
Former-commit-id: df8d5b6985
2024-08-27 11:30:16 +08:00
marko1616
53a2b16c38 Update chat.py
Former-commit-id: 1545684c3f
2024-08-27 11:27:56 +08:00
hiyouga
c765292093 support liger kernel
Former-commit-id: 72bc8f0111
2024-08-27 11:20:14 +08:00
marko1616
f3778f65f8 Force re check.
Former-commit-id: 3a28521710
2024-08-23 14:43:18 +08:00
marko1616
95500687dd Update chat.py
Former-commit-id: 8eb2092921
2024-08-22 12:24:34 +08:00
marko1616
7f6d267e98 Update chat.py
Former-commit-id: a4f1de9d82
2024-08-22 12:14:34 +08:00
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