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...
c996881
qwerrwe
/
src
/
axolotl
/
core
100 contributors
History:
73 commits
winglian
add support for rpo_alpha (#1681)
c996881
unverified
8 months ago
trainers
RL/DPO (#935)
about 1 year ago
__init__.py
Safe
0 Bytes
refactor setup trainer so we can add more hooks (#773)
over 1 year ago
trainer_builder.py
66.1 kB
add support for rpo_alpha (#1681)
8 months ago