Hugging Face's logo

albertfares
/
MNLP_M3_dpo_model_69k

PyTorch
Safetensors
qwen3
fdpo
mnlp
math
code
Model card Files
xet
Community
1
MNLP_M3_dpo_model_69k / tokenizer.json

Commit History

Upload fDPO trained Qwen3-0.6B model on MNLP M3 dataset (69k samples)
cc1fd2a
verified

albertfares commited on