Hugging Face's logo

MInAlA
/
Qwen3-4B-Instruct-2507-DPO-merged

Text Generation
Transformers
Safetensors
qwen3
trl
dpo
conversational
text-generation-inference
Model card Files
xet
 Community

Qwen3-4B-Instruct-2507 aligned using DPO on the argilla/ultrafeedback-binarized-preferences

Downloads last month
360
Safetensors
Model size
4B 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/Qwen3-4B-Instruct-2507-DPO-merged

Base model

Qwen/Qwen3-4B-Instruct-2507
Finetuned
(1537)
this model

Dataset used to train MInAlA/Qwen3-4B-Instruct-2507-DPO-merged