miitarou
/

qwen3-4b-structeval-v10

Text Generation

structured-output

Model card Files Files and versions

qwen3-4b-structeval-v10

V9 fix: enable_thinking=False to prevent tool_call contamination.

lr=5e-05, epochs=2, r=64, alpha=128, BS=32

Downloads last month: 19

Safetensors

Model size

4B params

Tensor type

BF16

·

Model tree for miitarou/qwen3-4b-structeval-v10

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(892)

this model

Dataset used to train miitarou/qwen3-4b-structeval-v10