Model Details

This is a finetune of Qwen/Qwen3-4B-Instruct-2507 using the HumanLLMs/Human-Like-DPO-Dataset dataset to make the model sound a lot friendly.

Safetensors

Model size

4B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for rex099/Human-Like-DPO-Qwen3-4B-Instruct-2507

Base model

Finetuned

(257)

this model

Merges

Quantizations