Commit Graph

2177 Commits

Author SHA1 Message Date
naem1023 209313eeea feat: add batch size of map function in the preprocessed dataset 2024-09-02 13:52:47 +09:00
hoshi-hiyouga 99fd9637bd
fix trainer predict 2024-09-02 10:15:29 +08:00
hoshi-hiyouga a6c6750e8a
remove .cpu() 2024-09-02 10:10:53 +08:00
hiyouga 60fc6b926e fix mm inference 2024-09-02 01:47:40 +08:00
hiyouga 3a6f19f017 tiny fix 2024-09-02 01:33:22 +08:00
hiyouga ce8c5a2647 add image num check 2024-09-02 01:31:36 +08:00
hiyouga 194064fdae add pokemon dataset 2024-09-02 01:02:25 +08:00
hiyouga a8f8a2ad8a update readme 2024-09-01 23:32:39 +08:00
hiyouga 753c5fb36c update wechat 2024-09-01 23:30:57 +08:00
hoshi-hiyouga 6f9e455af4
Merge pull request #5317 from ByronHsu/patch-1
Add liger kernel link
2024-09-01 23:30:12 +08:00
hiyouga 8e49940746 add rlhf-v dataset 2024-09-01 22:57:41 +08:00
hiyouga 55027282cd tiny fix 2024-09-01 21:15:44 +08:00
hiyouga 64cb947c60 fix bug 2024-09-01 21:07:49 +08:00
hiyouga 9967ccb3ae fix mixed mm inputs and rlhf-v 2024-09-01 20:52:47 +08:00
Byron Hsu b8a9cb554e
Add liger kernel link 2024-08-30 17:16:16 -07:00
hiyouga b5063b4144 fix ci (temp) 2024-08-31 02:03:56 +08:00
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