Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
Dovakiins
/
qwerrwe
like
0
Build error
App
Files
Files
Community
73f1bda
qwerrwe
/
src
/
axolotl
/
core
100 contributors
History:
39 commits
Philip May
Add more save strategies for DPO training. (#1255)
13eea21
unverified
10 months ago
trainers
RL/DPO (#935)
11 months ago
__init__.py
0 Bytes
refactor setup trainer so we can add more hooks (#773)
about 1 year ago
trainer_builder.py
44.4 kB
Add more save strategies for DPO training. (#1255)
10 months ago
