 Kai Wu
|
7ebd68c27d
Add llama 3.2 mmlu, math, gpqa evals to meta_eval harness (#801)
|
9 maanden geleden |
 Aidan Do
|
ab1b1450d7
Add gpqa and math evals for instruct models
|
9 maanden geleden |
|
Aidan Do
|
6224bd56c2
update comment
|
9 maanden geleden |
|
Aidan Do
|
b442625bf6
ensure pretrain_.yaml is udpated
|
9 maanden geleden |
|
Aidan Do
|
4f9050f748
Add mmlu eval for llama 3.2 pretrained models
|
10 maanden geleden |
|
Kai Wu
|
2f72bcec0d
[docs] small typo in eval readme (#796)
|
10 maanden geleden |
 Jayson Francis
|
008b8e45d5
small typo in eval README
|
10 maanden geleden |
|
Kai Wu
|
de3e32c8a7
fix typo in auto wrap policy (#793)
|
10 maanden geleden |
|
Kai Wu
|
7579b61d44
All functionality has been consolidated into a single file for CLI/UI/Checkpointing and Added fix for issue 702 and added code for that as well, added instructions in local_inference /README.md as well (#757)
|
10 maanden geleden |
|
Kai Wu
|
e5662e5804
add freeze_LLM_only option for mllama finetuning (#791)
|
10 maanden geleden |
 Jeff Tang
|
39bfabf634
add TogetherNotebookLM recipe (#766)
|
10 maanden geleden |
|
Jeff Tang
|
d437411cf5
added pydantic to wordlist.txt
|
10 maanden geleden |
 Guanghui Qin
|
a62aff3876
fix typo in auto wrap policy
|
10 maanden geleden |
 JimChienTW
|
d31ee18e4f
Print model's frozen status after freezing
|
10 maanden geleden |
 Himanshu Shukla
|
54269639de
added inference instructions in README for easy inferencing
|
10 maanden geleden |
|
Himanshu Shukla
|
3ba4b64e71
shifted the import statement at top
|
10 maanden geleden |
|
Himanshu Shukla
|
2df7d1b6a8
fixed the issue of everytime login
|
10 maanden geleden |
|
Himanshu Shukla
|
db3216695a
Added the huggingface cli feature
|
10 maanden geleden |
|
JimChienTW
|
d1195a6fd8
Fix model parameter mismatch by printing parameters before FSDP
|
10 maanden geleden |
 Himanshu Shukla
|
3e1d9856ff
Merge branch 'meta-llama:main' into main
|
10 maanden geleden |
 Sanyam Bhutani
|
4250439387
colab links fix (#790)
|
10 maanden geleden |
|
JimChienTW
|
f228cb4d53
update README
|
10 maanden geleden |
|
JimChienTW
|
21e8368c7e
add freeze_LLM_only option for mllama finetuning
|
10 maanden geleden |
|
Himanshu Shukla
|
06ea2a7a6f
Merge branch 'meta-llama:main' into main
|
10 maanden geleden |
|
Jeff Tang
|
b579bd04a8
colab links fix
|
10 maanden geleden |
 Suraj Subramanian
|
b9fc10696c
fix walkthrough.ipynb render (#787)
|
10 maanden geleden |
|
Suraj Subramanian
|
9c7e1d0692
fix walkthrough.ipynb render
|
10 maanden geleden |
|
Himanshu Shukla
|
6b6bb37ecd
fixed gradio UI during performing the tests, it is working in this commit
|
10 maanden geleden |
|
Himanshu Shukla
|
20dd474056
added working code of CLI/gradio UI/ LoRA weights merge
|
10 maanden geleden |
|
Himanshu Shukla
|
243332539e
Renamed file from code-merge-inference.py to multi_modal_infer.py
|
10 maanden geleden |
