Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
LahiruWije
/
Qwen2.5-0.5B-Instruct-GPRO-GSM8K
like
0
Question Answering
Transformers
PyTorch
Safetensors
openai/gsm8k
English
qwen2
text-generation
unsloth
trl
grpo
reasoning
gsm8k
text-generation-inference
arxiv:
2402.03300
License:
apache-2.0
Model card
Files
Files and versions
Community
2
Train
Deploy
Use this model
main
Qwen2.5-0.5B-Instruct-GPRO-GSM8K
/
merges.txt
Commit History
Upload tokenizer
8a7f9a1
verified
LahiruWije
commited on
Mar 1