Hugging Face's logo

MInAlA
/
Llama-3.2-3B-DPO-merged

Text Generation
Transformers
Safetensors
llama
trl
dpo
conversational
text-generation-inference
Model card Files
xet
 Community

Llama-3.2-3B-Instruct aligned using DPO on the argilla/ultrafeedback-binarized-preferences

Downloads last month
289
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/Llama-3.2-3B-DPO-merged

Base model

meta-llama/Llama-3.2-3B-Instruct
Finetuned
(1529)
this model

Dataset used to train MInAlA/Llama-3.2-3B-DPO-merged