Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
Dovakiins
/
qwerrwe
like
0
Build error
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
590d603
qwerrwe
/
src
/
axolotl
/
utils
100 contributors
History:
329 commits
ich
Fix bug when using pretokenized datasets (#652)
590d603
unverified
over 1 year ago
__init__.py
Safe
0 Bytes
WIP large refactor to make finetune script a little more manageable (#3)
almost 2 years ago
bench.py
Safe
2.06 kB
misc fixes to add gptq tests (#621)
over 1 year ago
callbacks.py
Safe
19.8 kB
chore(callback): Remove old peft saving code (#510)
over 1 year ago
collators.py
Safe
5.39 kB
Attention mask and position id fixes for packing (#285)
over 1 year ago
config.py
13.2 kB
Fix bug when using pretokenized datasets (#652)
over 1 year ago
data.py
25 kB
add support for defined train split (#654)
over 1 year ago
dataloader.py
Safe
9.94 kB
gracefully handle length feature used for group by (#565)
over 1 year ago
dict.py
Safe
326 Bytes
fix DefaultDict.__or__
over 1 year ago
distributed.py
Safe
6.87 kB
fix distributed devices (#612)
over 1 year ago
models.py
20.8 kB
Mistral flash attn packing (#646)
over 1 year ago
schedulers.py
Safe
3.58 kB
add axolotl trainer and quadratic warmup
over 1 year ago
tokenization.py
1.42 kB
use fastchat conversations template (#578)
over 1 year ago
trainer.py
29.6 kB
Fix(cfg): Add validation for save_strategy and eval_strategy (#633)
over 1 year ago
wandb_.py
Safe
858 Bytes
fix wandb so mypy doesn't complain (#562)
over 1 year ago