Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
BiXie
/
next
like
0
License:
apache-2.0
Model card
Files
Files and versions
Community
main
next
/
trl
/
trainer
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
BiXie
Upload 204 files
252711e
verified
8 months ago
__pycache__
Upload 204 files
8 months ago
__init__.py
1.51 kB
Upload 204 files
8 months ago
base.py
1.82 kB
Upload 204 files
8 months ago
ddpo_config.py
4.93 kB
Upload 204 files
8 months ago
ddpo_trainer.py
27 kB
Upload 204 files
8 months ago
dpo_trainer.py
62.6 kB
Upload 204 files
8 months ago
iterative_sft_trainer.py
16.5 kB
Upload 204 files
8 months ago
model_config.py
2.97 kB
Upload 204 files
8 months ago
ppo_config.py
8.32 kB
Upload 204 files
8 months ago
ppo_trainer.py
63.2 kB
Upload 204 files
8 months ago
reward_config.py
1.66 kB
Upload 204 files
8 months ago
reward_trainer.py
13.6 kB
Upload 204 files
8 months ago
sft_trainer.py
24.7 kB
Upload 204 files
8 months ago
utils.py
32 kB
Upload 204 files
8 months ago