 Kai Wu
|
8a11b48022
lora+fsdp not working
|
hai 1 ano |
|
Kai Wu
|
79dbe05a94
batch fine-tuning lmm working
|
hai 1 ano |
|
Kai Wu
|
ce299b3439
add get_custom_data_collator feature
|
hai 1 ano |
|
Kai Wu
|
12da109823
Merge branch 'main' into lmm_finetune
|
hai 1 ano |
|
Kai Wu
|
bb990be967
not working, need create dataloader function
|
hai 1 ano |
 Matthias Reso
|
d9939cd0cf
Fix to take bos into account
|
hai 1 ano |
|
Kai Wu
|
c38cccb66f
readme draft
|
hai 1 ano |
|
Matthias Reso
|
3c9f263c79
Mask out assistant header
|
hai 1 ano |
 Suraj Subramanian
|
acac5257cd
Merge branch 'main' of https://github.com/meta-llama/llama-recipes into llama-triage-tool
|
hai 1 ano |
|
Suraj Subramanian
|
713206fdab
improve readability, logging, fix spellcheck test
|
hai 1 ano |
|
Matthias Reso
|
a38a80a252
Remove debug prints
|
hai 1 ano |
|
Matthias Reso
|
d45222ec1a
Add unit test for tokenizer_dialog for custom dataset
|
hai 1 ano |
|
Matthias Reso
|
dadadf8387
Fix custom dataset after default system prompt was added
|
hai 1 ano |
 Jeff Tang
|
3e39ed05bd
Update get_default_finetune_args.py (#662)
|
hai 1 ano |
|
Kai Wu
|
abe44c0237
fix the idx issue for labels
|
hai 1 ano |
 Eda Z
|
9b3c4f8d50
Update get_default_finetune_args.py
|
hai 1 ano |
 Gautam Kumar
|
ccd4741084
Adding custom dataset file (#659)
|
hai 1 ano |
|
Matthias Reso
|
778e31e35c
Fix checkpoint saving (#650)
|
hai 1 ano |
|
Kai Wu
|
ee204ccb98
working now
|
hai 1 ano |
|
Kai Wu
|
b566582a86
finetune not working with fsdp
|
hai 1 ano |
|
Suraj Subramanian
|
8ddcfd8ecd
update docs
|
hai 1 ano |
|
Suraj Subramanian
|
49d6af9e4d
Merge branch 'main' of https://github.com/meta-llama/llama-recipes into llama-triage-tool
|
hai 1 ano |
|
Suraj Subramanian
|
cd31ee99ac
* Add logging
|
hai 1 ano |
|
Suraj Subramanian
|
a5ddea144a
Add auto triage tooll
|
hai 1 ano |
 Sanyam Bhutani
|
04766dcf2a
Fix version number in Python example (#643)
|
hai 1 ano |
 wstnmssr
|
0f632b3e3d
Fix version number in Python example
|
hai 1 ano |
 Hamid Shojanazeri
|
b5f64c0b69
Eval reproduce recipe using lm-evaluation-harness and our 3.1 evals datasets (#627)
|
hai 1 ano |
|
Kai Wu
|
e354eee1fb
minor fix
|
hai 1 ano |
|
Sanyam Bhutani
|
eaded5edcc
document less obvious training config parameters (#522)
|
hai 1 ano |
 Kevin Slagle
|
52a85e1564
merge
|
hai 1 ano |
