Hugging Face's logo

albertfares
/
MNLP_M3_dpo_model

Text Generation
PyTorch
Safetensors
English
qwen3
dpo
fdpo
math
code
reasoning
conversational
Model card Files
xet
Community
MNLP_M3_dpo_model / tokenizer_config.json

Commit History

Upload fDPO trained Qwen3-0.6B model on MNLP M3 dataset (69k samples)
4f3038c
verified

albertfares commited on