Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
neopolita
/
qwen2.5-3b-instruct-numinamath-tir-20p-lr16-la32-qkvo-gspo
like
0
Transformers
Safetensors
Generated from Trainer
grpo
trl
arxiv:
2402.03300
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
qwen2.5-3b-instruct-numinamath-tir-20p-lr16-la32-qkvo-gspo
/
vocab.json
Commit History
Training in progress, step 10
ed3c585
verified
neopolita
commited on
Aug 1