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...
ace70b3
qwerrwe
/
src
/
axolotl
100 contributors
History:
439 commits
Nanobit
Fix: Higher vram usage for mistral and sample_packing (#691)
669f1d0
unverified
over 1 year ago
cli
prepared dataset caching, other misc fixes (#665)
over 1 year ago
common
Debug tokenization output: Add ability to output text only (no tokens), and/or specify num samples to see (#511)
over 1 year ago
models
attention_mask not needed for training (#642)
over 1 year ago
monkeypatch
flash_attention + sample packing for stablelm 3b (#671)
over 1 year ago
prompt_strategies
add support for defined train split (#654)
over 1 year ago
utils
Fix: Higher vram usage for mistral and sample_packing (#691)
over 1 year ago
__init__.py
Safe
0 Bytes
WIP for axolotl trainer
almost 2 years ago
convert.py
Safe
1.88 kB
Lint convert.py
over 1 year ago
datasets.py
Safe
6.93 kB
Correct typos in datasets.py (#639)
over 1 year ago
logging_config.py
Safe
1.88 kB
log rank too (#527)
over 1 year ago
prompt_tokenizers.py
16.4 kB
don't strip the prompt for check since we don't strip to tokenize anymore (#650)
over 1 year ago
prompters.py
12 kB
use fastchat conversations template (#578)
over 1 year ago
train.py
Safe
5.45 kB
create a model card with axolotl badge (#624)
over 1 year ago