Commit Graph

2061 Commits

Author SHA1 Message Date
hiyouga
a2a8c0b92c add test mm plugin 2024-08-31 01:53:38 +08:00
hiyouga
a025c3df61 remove visual_inputs, fix qlora 2024-08-31 00:24:51 +08:00
hiyouga
a244f143f4 optimize predict vram 2024-08-30 23:08:45 +08:00
hiyouga
e08045a946 add examples 2024-08-30 21:43:19 +08:00
hiyouga
bee1bd43b9 tiny fix 2024-08-30 03:21:50 +08:00
hiyouga
8b588c7224 fix #5307 2024-08-30 02:45:40 +08:00
hiyouga
3382317e32 refactor mm training 2024-08-30 02:14:31 +08:00
hoshi-hiyouga
727e184840 Merge pull request #5290 from simonJJJ/qwen2_vl
support qwen2-vl
2024-08-30 02:10:36 +08:00
hoshi-hiyouga
a8f22d8895 fix bug 2024-08-30 02:05:26 +08:00
hiyouga
a7dd7d325e update liger kernel 2024-08-29 20:46:08 +08:00
hiyouga
aa1afdc756 fix #5292 2024-08-29 20:37:47 +08:00
hiyouga
ad72f3e065 fix #5295 2024-08-29 20:30:18 +08:00
hiyouga
364b757e30 fix #5305 2024-08-29 20:16:01 +08:00
simonJJJ
734e019cc1 update 2024-08-28 20:22:46 +08:00
simonJJJ
aeb85f200b initial-commit 2024-08-28 16:51:35 +08:00
hiyouga
0f5a0f64f7 update wechat 2024-08-27 12:55:23 +08:00
hiyouga
d14edd350d add extra requires 2024-08-27 12:52:12 +08:00
hiyouga
f6ae4e75dd tiny fix 2024-08-27 12:49:32 +08:00
hoshi-hiyouga
dbe886ae5c Merge pull request #5237 from marko1616/patch-1
Fix mllm api
2024-08-27 12:24:43 +08:00
marko1616
df8d5b6985 ruff pass. 2024-08-27 11:30:16 +08:00
marko1616
1545684c3f Update chat.py 2024-08-27 11:27:56 +08:00
hiyouga
72bc8f0111 support liger kernel 2024-08-27 11:20:14 +08:00
marko1616
3a28521710 Force re check. 2024-08-23 14:43:18 +08:00
marko1616
8eb2092921 Update chat.py 2024-08-22 12:24:34 +08:00
marko1616
a4f1de9d82 Update chat.py 2024-08-22 12:14:34 +08:00
hoshi-hiyouga
36039b0fe0 Merge pull request #5230 from MengqingCao/image
[NPU] Update npu base image
2024-08-21 22:13:07 +08:00
hiyouga
8907150c1b update wechat 2024-08-21 22:07:34 +08:00
MengqingCao
b3f4acd1b4 update npu base image 2024-08-21 09:12:38 +00:00
hiyouga
c8b4c7fee5 tiny fix 2024-08-20 00:10:52 +08:00
hoshi-hiyouga
15be296347 Merge pull request #5156 from YeQiuO/main
fix Llama-template's system prompt bug
2024-08-20 00:09:03 +08:00
hoshi-hiyouga
ec72eeca52 Update template.py 2024-08-20 00:03:33 +08:00
hoshi-hiyouga
da335d42c3 Merge pull request #5163 from liu-zichen/fix_ppo_optim
fix lr not change
2024-08-19 23:56:24 +08:00
hoshi-hiyouga
f59c9bef31 Merge pull request #5185 from chenhuiyu/feature/add-sailorllm-template
Add SailorLLM template
2024-08-19 23:51:49 +08:00
hoshi-hiyouga
d39f4a62d3 Merge pull request #5188 from Zxilly/main
fix: report correct device count for intel xpu
2024-08-19 23:51:39 +08:00
hoshi-hiyouga
5d5bfc83e6 Merge pull request #5193 from Ricardo-L-C/main
_is_bf16_available judgment supports npu
2024-08-19 23:40:59 +08:00
hoshi-hiyouga
5f3300ec5d Update template.py 2024-08-19 23:40:16 +08:00
hiyouga
3804ddec9e update readme 2024-08-19 23:32:04 +08:00
Ricardo
384ab8db84 _is_bf16_available judgment supports npu 2024-08-16 02:58:22 +00:00
Zxilly
dc36fcc3de fix: report correct device count for intel xpu 2024-08-15 08:30:43 +00:00
Huiyu Chen
2502833a77 Add SailorLLM template 2024-08-15 15:10:14 +08:00
liu-zichen
ddee718b31 fix lr not change 2024-08-13 16:33:34 +08:00
codingma
625a0e32c4 add tutorial and doc links 2024-08-13 16:13:10 +08:00
codingma
5b9d99ebc6 update wechat.jpg 2024-08-13 16:12:36 +08:00
“Wzw”
bcbbf45063 fix Llama-template's system prompt bug 2024-08-12 19:22:12 +08:00
hiyouga
c93d55bfb0 update readme 2024-08-10 10:17:35 +08:00
hiyouga
576a894f77 update readme 2024-08-09 20:46:02 +08:00
hiyouga
c75b5b83c4 add magpie ultra dataset 2024-08-09 20:28:55 +08:00
hiyouga
dc770efb14 add qwen2 math models 2024-08-09 20:20:35 +08:00
hiyouga
0a690ada6f update examples 2024-08-09 20:13:46 +08:00
hiyouga
e2a28f51c6 add adam_mini to readme 2024-08-09 20:02:03 +08:00