Hugging Face's logo

MInAlA
/
SmolLM3-3B-DPO-merged

Text Generation
Transformers
Safetensors
smollm3
trl
dpo
conversational
Model card Files
xet
 Community

Smollm3-3B aligned using DPO on the argilla/ultrafeedback-binarized-preferences

Downloads last month
623
Safetensors
Model size
3B params
Tensor type
BF16
·
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MInAlA/SmolLM3-3B-DPO-merged

Base model

HuggingFaceTB/SmolLM3-3B-Base
Finetuned
HuggingFaceTB/SmolLM3-3B
Finetuned
(124)
this model

Dataset used to train MInAlA/SmolLM3-3B-DPO-merged