Instructions to use oscarzhang/HealthRecommendationGGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oscarzhang/HealthRecommendationGGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="oscarzhang/HealthRecommendationGGUF",
	filename="health_advisor_qwen3_4b.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use oscarzhang/HealthRecommendationGGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf oscarzhang/HealthRecommendationGGUF
# Run inference directly in the terminal:
llama-cli -hf oscarzhang/HealthRecommendationGGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf oscarzhang/HealthRecommendationGGUF
# Run inference directly in the terminal:
llama-cli -hf oscarzhang/HealthRecommendationGGUF

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 oscarzhang/HealthRecommendationGGUF
# Run inference directly in the terminal:
./llama-cli -hf oscarzhang/HealthRecommendationGGUF

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 oscarzhang/HealthRecommendationGGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf oscarzhang/HealthRecommendationGGUF

Use Docker

docker model run hf.co/oscarzhang/HealthRecommendationGGUF

LM Studio
Jan
Ollama
How to use oscarzhang/HealthRecommendationGGUF with Ollama:
```
ollama run hf.co/oscarzhang/HealthRecommendationGGUF
```

Unsloth Studio new

How to use oscarzhang/HealthRecommendationGGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for oscarzhang/HealthRecommendationGGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for oscarzhang/HealthRecommendationGGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for oscarzhang/HealthRecommendationGGUF to start chatting

Pi new

How to use oscarzhang/HealthRecommendationGGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf oscarzhang/HealthRecommendationGGUF

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "oscarzhang/HealthRecommendationGGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use oscarzhang/HealthRecommendationGGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf oscarzhang/HealthRecommendationGGUF

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default oscarzhang/HealthRecommendationGGUF

Run Hermes

hermes

Docker Model Runner
How to use oscarzhang/HealthRecommendationGGUF with Docker Model Runner:
```
docker model run hf.co/oscarzhang/HealthRecommendationGGUF
```

Lemonade

How to use oscarzhang/HealthRecommendationGGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull oscarzhang/HealthRecommendationGGUF

Run and chat with the model

lemonade run user.HealthRecommendationGGUF-{{QUANT_TAG}}

List all available models

lemonade list

Health Recommendation Model - GGUF Format

这是健康推荐模型的 GGUF 格式版本，基于 Qwen3-VL-4B-Instruct 微调。

模型信息

基础模型: Qwen/Qwen3-VL-4B-Instruct
格式: GGUF (用于 llama.cpp / Ollama)
量化: Q8_0 (高质量)
文件大小: ~4.0 GB
语言: 中文 (Chinese)

使用方法

使用 Ollama

模型已经适配为可以在 Ollama 中使用：

# 如果已安装 Ollama
ollama run health-advisor "请基于症状信息，生成个性化的健康干预方案。粗症状：疲劳"

使用 llama.cpp

# 下载模型
huggingface-cli download oscarzhang/HealthRecommendationGGUF health_advisor_qwen3_4b.gguf --local-dir .

# 使用 llama.cpp 运行
./llama-cli -m health_advisor_qwen3_4b.gguf -p "请基于症状信息，生成个性化的健康干预方案。粗症状：疲劳"

模型特点

专门针对健康干预方案生成进行微调
基于理论框架: 使用 P3 框架和 PROCEED 框架
三个维度干预: 生活方式、心理、环境
可量化评估指标: 提供可测量的评估指标

使用限制

⚠️ 重要提示：

本模型仅提供生活干预建议，不做医疗诊断
不应用于紧急医疗情况
对于需要医疗干预的情况，必须明确指出需要就医
不应替代专业医疗建议

训练信息

训练方法: LoRA (Low-Rank Adaptation)
训练数据: 126 条健康干预方案样本
训练步数: 100 步
最终 Loss: 0.7 (从 2.5 下降到 0.7)

许可证

Apache 2.0 (继承自基础模型)

Downloads last month: 3

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for oscarzhang/HealthRecommendationGGUF

Base model

Qwen/Qwen3-VL-4B-Instruct

Quantized

(70)

this model

oscarzhang
/

HealthRecommendationGGUF