Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
PumpkinCat
/
SmolLM3-SFT-repoc-DPO
like
0
Text Generation
Transformers
Safetensors
smollm3
Generated from Trainer
dpo
trl
conversational
arxiv:
2305.18290
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
SmolLM3-SFT-repoc-DPO
/
tokenizer.json
Commit History
Training in progress, step 2647
548099d
verified
PumpkinCat
commited on
Dec 21, 2025