Tkawamura
/

test-lora-repo

Text Generation

text-generation-inference

Model card Files Files and versions

qwen3-4b-dpo-merged-model

This model is a fine-tuned version of Qwen/Qwen3-4B-Instruct-2507.

Training Configuration

Method: DPO
Epochs: 1
Learning rate: 1e-6
Max length: 512

Downloads last month: 29

Safetensors

Model size

4B params

Tensor type

BF16

·

Model tree for Tkawamura/test-lora-repo

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1413)

this model

Dataset used to train Tkawamura/test-lora-repo