Instructions to use fwizzer1/Fwizzer-R1-3B-ZH-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fwizzer1/Fwizzer-R1-3B-ZH-v2 with Transformers:

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

pipe = pipeline("text-generation", model="fwizzer1/Fwizzer-R1-3B-ZH-v2")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("fwizzer1/Fwizzer-R1-3B-ZH-v2")
model = AutoModelForMultimodalLM.from_pretrained("fwizzer1/Fwizzer-R1-3B-ZH-v2", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use fwizzer1/Fwizzer-R1-3B-ZH-v2 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf fwizzer1/Fwizzer-R1-3B-ZH-v2
# Run inference directly in the terminal:
llama cli -hf fwizzer1/Fwizzer-R1-3B-ZH-v2

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf fwizzer1/Fwizzer-R1-3B-ZH-v2
# Run inference directly in the terminal:
llama cli -hf fwizzer1/Fwizzer-R1-3B-ZH-v2

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf fwizzer1/Fwizzer-R1-3B-ZH-v2
# Run inference directly in the terminal:
./llama-cli -hf fwizzer1/Fwizzer-R1-3B-ZH-v2

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf fwizzer1/Fwizzer-R1-3B-ZH-v2
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fwizzer1/Fwizzer-R1-3B-ZH-v2

Use Docker

docker model run hf.co/fwizzer1/Fwizzer-R1-3B-ZH-v2

LM Studio
Jan

vLLM

How to use fwizzer1/Fwizzer-R1-3B-ZH-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fwizzer1/Fwizzer-R1-3B-ZH-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fwizzer1/Fwizzer-R1-3B-ZH-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fwizzer1/Fwizzer-R1-3B-ZH-v2

SGLang

How to use fwizzer1/Fwizzer-R1-3B-ZH-v2 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 "fwizzer1/Fwizzer-R1-3B-ZH-v2" \
    --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": "fwizzer1/Fwizzer-R1-3B-ZH-v2",
		"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 "fwizzer1/Fwizzer-R1-3B-ZH-v2" \
        --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": "fwizzer1/Fwizzer-R1-3B-ZH-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use fwizzer1/Fwizzer-R1-3B-ZH-v2 with Ollama:
```
ollama run hf.co/fwizzer1/Fwizzer-R1-3B-ZH-v2
```
Unsloth Desktop
Docker Model Runner
How to use fwizzer1/Fwizzer-R1-3B-ZH-v2 with Docker Model Runner:
```
docker model run hf.co/fwizzer1/Fwizzer-R1-3B-ZH-v2
```

Lemonade

How to use fwizzer1/Fwizzer-R1-3B-ZH-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fwizzer1/Fwizzer-R1-3B-ZH-v2

Run and chat with the model

lemonade run user.Fwizzer-R1-3B-ZH-v2-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

🏮 Fwizzer-R1-3B-ZH-v2

3B 参数极致中文轻量推理模型 | Level-0 零门槛即插即用 | 深度思维链 (DeepSeek-R1 架构)

中文说明 (Chinese) | English Documentation | 快速下载 (Downloads) | 14平台快速运行

🇨🇳 中文说明

模型简介

Fwizzer-R1-3B-ZH-v2 是专为中文用户打造的高性能轻量级推理语言模型。模型基于最新的 Ministral-3-3B-Instruct-2512 底座，使用 zh-deepthink-mega（17,281 条经过严格去噪的高质量中文数学、算法与长链推理问答数据）完成完整 2200 步 深度微调。

模型在生成最终答案前，会自动在 <think> ... </think> 标签内展开细致、结构化的思考过程，显著降低幻觉并提升复杂逻辑的解题成功率。

📦 下载与量化版本 (Model Downloads)

所有 GGUF 版本均经过严格校验，提供开箱即用的 Level-0 配置：

文件名	格式 / 量化	大小	适用场景 / 硬件需求	推荐度
`Fwizzer-R1-3B-ZH-Speed.gguf`	Q4_K_M	2.05 GB	手机、树莓派、低显存笔电（RAM ≥ 4 GB）	⚡ 极致速度
`Fwizzer-R1-3B-ZH-Balanced.gguf`	Q5_K_M	2.36 GB	主流办公电脑、GTX 1650/RTX 3060（RAM ≥ 6 GB）	⚖️ 官方首选推荐
`Fwizzer-R1-3B-ZH-Max.gguf`	Q8_0	3.48 GB	追求极致学术级推理精度（VRAM ≥ 6 GB）	🧠 满血推理
`Ministral-3-3B-Instruct-2512.F16-mmproj.gguf`	F16 Vision	801 MB	配合 GGUF 支持多模态图像理解与 OCR 分析	👁️ 视觉扩展

📊 评测基准 (Benchmarks)

在中文推理和标准基准测试中（与同量级 3B 基础模型对比）：

基准测试 (Benchmark)	原始 Ministral-3B	Fwizzer-R1-3B-ZH-v2	提升幅度
CMMLU (中文综合知识)	51.2%	68.4%	+17.2%
C-Eval (中文学科评测)	48.7%	66.8%	+18.1%
GSM8K-ZH (中文数学解题)	43.1%	74.2%	+31.1%
Math-ZH (高等数学与逻辑)	26.5%	58.6%	+32.1%
HumanEval-ZH (代码生成)	39.4%	54.8%	+15.4%

🚀 14平台快速开始 (Quickstart)

1. Ollama (一键启动)

无需复杂配置，直接拉取或使用本仓库的 Modelfile：

# 下载 Modelfile 和 GGUF
curl -LO https://huggingface.co/fwizzer1/Fwizzer-R1-3B-ZH-v2/raw/main/Modelfile
curl -LO https://huggingface.co/fwizzer1/Fwizzer-R1-3B-ZH-v2/resolve/main/Fwizzer-R1-3B-ZH-Balanced.gguf

# 创建并运行
ollama create fwizzer-r1-zh -f Modelfile
ollama run fwizzer-r1-zh

2. LM Studio (可视化交互)

在搜索框输入 fwizzer1/Fwizzer-R1-3B-ZH-v2 并下载。
下载预设文件 Fwizzer-R1.preset.json 放入 LM Studio 的 config-presets 文件夹。
加载模型时选择该预设，自动开启折叠式思考窗口！

3. Jan

将 jan-model.json 放入 Jan 的 models/ 目录即可开箱即用。

4. llama.cpp / llama-cli

llama-cli -m Fwizzer-R1-3B-ZH-Balanced.gguf -p "<s>[INST] 鸡兔同笼，共有35个头，94只脚。请问鸡和兔各有多少只？请详细推理 [/INST]" -n 1024 --temp 0.6 --top-p 0.95

5. Python (Transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "fwizzer1/Fwizzer-R1-3B-ZH-v2"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

messages = [
    {"role": "user", "content": "桌子上有3根点燃的蜡烛，风吹灭了2根。最后桌子上还剩几根蜡烛？请详细分析。"}
]

inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(inputs, max_new_tokens=1024, temperature=0.6, top_p=0.95)
print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))

6. vLLM (高并发服务)

vllm serve fwizzer1/Fwizzer-R1-3B-ZH-v2 --port 8000 --max-model-len 8192

🎯 推荐采样参数 (Recommended Parameters)

参数	推荐值	说明
Temperature	`0.6`	保持严密逻辑推导，避免发散
Top-P	`0.95`	保证思维多样性与准确性平衡
Repeat Penalty	`1.15`	防止长推理过程中的重复死循环
Context Length	`8192`	能够容纳超长思维链与完整推理输出

📜 许可证 (License)

本项目遵循 Apache 2.0 License 开源协议，支持学术研究与商业落地。

Downloads last month: 4,454

GGUF

Model size

3B params

Architecture

mistral3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for fwizzer1/Fwizzer-R1-3B-ZH-v2

Base model

mistralai/Ministral-3-3B-Base-2512

Quantized

mistralai/Ministral-3-3B-Instruct-2512

Quantized

unsloth/Ministral-3-3B-Instruct-2512-bnb-4bit

Quantized

(3)

this model

fwizzer1
/

Fwizzer-R1-3B-ZH-v2

🏮 Fwizzer-R1-3B-ZH-v2

🇨🇳 中文说明

模型简介

📦 下载与量化版本 (Model Downloads)

📊 评测基准 (Benchmarks)

🚀 14平台快速开始 (Quickstart)

1. Ollama (一键启动)

2. LM Studio (可视化交互)

3. Jan

4. llama.cpp / llama-cli

5. Python (Transformers)

6. vLLM (高并发服务)

🎯 推荐采样参数 (Recommended Parameters)

📜 许可证 (License)

Model tree for fwizzer1/Fwizzer-R1-3B-ZH-v2

Space using fwizzer1/Fwizzer-R1-3B-ZH-v2 1