yykx
/

wrj-combine-v23

safety-alignment

Model card Files Files and versions

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

wrj-combine-v23

基于 Qwen/Qwen3-0.6B 的 LoRA 微调模型，浙江大学网安夏令营项目实践考核提交产物。

基座模型：Qwen/Qwen3-0.6B
微调方法：LoRA（peft），r=16，alpha=32，dropout=0.05，target 全部 7 个线性层
训练目标：多目标联合微调（安全拒答 + 反过拒答 + 数学推理 + 通用对话）
作者：吴仁杰

推理时使用官方 Qwen3 chat template，enable_thinking=False。

Downloads last month: 4

Safetensors

Model size

0.6B params

Tensor type

BF16

·

Inference Providers NEW

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

Model tree for yykx/wrj-combine-v23

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Adapter

(562)

this model