Instructions to use Yy245/Qwen3-0.6B-SafeMath-ZJU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yy245/Qwen3-0.6B-SafeMath-ZJU with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Yy245/Qwen3-0.6B-SafeMath-ZJU")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Yy245/Qwen3-0.6B-SafeMath-ZJU")
model = AutoModelForCausalLM.from_pretrained("Yy245/Qwen3-0.6B-SafeMath-ZJU", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Yy245/Qwen3-0.6B-SafeMath-ZJU with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yy245/Qwen3-0.6B-SafeMath-ZJU"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yy245/Qwen3-0.6B-SafeMath-ZJU",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Yy245/Qwen3-0.6B-SafeMath-ZJU

SGLang

How to use Yy245/Qwen3-0.6B-SafeMath-ZJU with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Yy245/Qwen3-0.6B-SafeMath-ZJU" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yy245/Qwen3-0.6B-SafeMath-ZJU",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Yy245/Qwen3-0.6B-SafeMath-ZJU" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yy245/Qwen3-0.6B-SafeMath-ZJU",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Yy245/Qwen3-0.6B-SafeMath-ZJU with Docker Model Runner:
```
docker model run hf.co/Yy245/Qwen3-0.6B-SafeMath-ZJU
```

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.

Qwen3-0.6B-SafeMath-ZJU

这是 ZJU 考核最终用于评分的完整合并模型，基于 Qwen/Qwen3-0.6B 进行安全与数学推理联合微调。模型经过混合 SFT、失败驱动 SFT 和多目标 GRPO 三个阶段，最终选择固定评测加权分最高的 Round 3，而不是后续未通过防遗忘门禁的 Round 2b 或 Round 3b。

模型选择与结果

固定基座版本：c1899de289a04d12100db370d81485cdf75e47ca
最终模型：Round 3（GRPO）
参数量：596,049,920，与基座完全一致
权重 SHA-256：64f97589d3743bfd531adc08863bfaee14c5b3fb3056f0cd023ed28bc4943773
安全代理分：79.60%
数学均值（GSM8K / MATH-500）：36.00%
通用均值（MMLU / ARC-Challenge）：32.92%
加权总分：52.51%，高于 Round 2b 的 52.09% 和 Round 3b 的 51.03%

加权规则为 0.4 × 安全 + 0.3 × 数学 + 0.3 × 通用。详细逐轮结果见 evaluation/model_selection.json，重训分支审计见 evaluation/retrain_comparison.json。

与原始 Qwen3-0.6B 无缝兼容

本仓库上传的是完整合并权重，不需要 PEFT/LoRA 适配器。架构、词表、token ID、聊天模板、 thinking 开关和默认生成配置均与原始 Qwen/Qwen3-0.6B 兼容。原调用代码只需替换模型 ID：

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Yy245/Qwen3-0.6B-SafeMath-ZJU"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
)

messages = [{"role": "user", "content": "Give me a short introduction to large language models."}]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(**model_inputs, max_new_tokens=512)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):]
print(tokenizer.decode(output_ids, skip_special_tokens=True))

enable_thinking=False、多轮对话、pipeline、SGLang 和 vLLM 的调用方式也与原模型一致。例如原 vLLM 命令只需替换模型 ID：

vllm serve Yy245/Qwen3-0.6B-SafeMath-ZJU \
  --enable-reasoning --reasoning-parser deepseek_r1

建议使用 transformers>=4.51.0；thinking 模式可沿用原模型的默认采样设置（temperature 0.6、top-p 0.95、top-k 20）。

训练过程报告

完整的一页 PDF 可在 training_report.pdf 下载。

限制

这些分数来自固定代理评测，并不等同于真实部署中的绝对安全保证。模型仍可能对含糊但无害的请求过度拒答，也可能在较难数学题、长上下文或分布外输入上生成错误内容；高风险场景应继续使用独立安全策略、人工复核和领域评测。

Downloads last month: -

Safetensors

Model size

0.8B params

Tensor type

BF16

Model tree for Yy245/Qwen3-0.6B-SafeMath-ZJU

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

(1139)

this model