Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Spaces:

srishtichugh
/

orgOS

Sleeping

App Files Files Community

Fetching metadata from the HF Docker repository...

orgOS / training

137 kB

Ctrl+K

Ctrl+K

7 contributors

History: 7 commits

muskan singh

adding

f5c84e7 about 1 month ago

plots
adding about 1 month ago
grpo_orgos.ipynb

30.7 kB
fix: stable GRPO notebook — pin TRL<=0.24, multi-step reward, Drive checkpoints every 30 steps about 1 month ago
train.py

20.7 kB
plots, results, readme updations about 1 month ago