Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Spaces:
bird-of-paradise
/
ReTool-Implementation
like
1
Running
App
Files
Files
Community
main
ReTool-Implementation
/
src
136 kB
2 contributors
History:
8 commits
bird-of-paradise
Add custom sampler, train data loader and GRPO style train loop for ReTool_trainer
c710786
verified
4 months ago
test
adding test suite -- first commit
5 months ago
utils
first commit --curriculum callback
5 months ago
requirements.txt
Safe
374 Bytes
Upload 5 files
6 months ago
retool_trainer.py
Safe
49 kB
Add custom sampler, train data loader and GRPO style train loop for ReTool_trainer
4 months ago
rewards.py
Safe
6.4 kB
Add reward functions and registry
5 months ago