---
base_model: Qwen/Qwen3-VL-4B-Instruct
library_name: peft
tags:
- base_model:Qwen/Qwen3-VL-4B-Instruct
- lora
- transformers
- health-recommendation
- chinese
- healthcare
---

# Health Recommendation Model

一个基于 Qwen3-VL-4B-Instruct 的健康干预方案生成模型。

## Model Description

这个模型是专门针对健康推荐和干预方案生成任务进行微调的 LoRA 适配器。它能够根据用户提供的症状信息，生成个性化的健康干预方案，包括生活方式建议、心理干预和环境改造建议。

### 主要功能

- **症状分析**: 基于用户提供的症状信息进行分析
- **干预方案生成**: 生成包含生活方式、心理、环境三个维度的干预建议
- **理论依据**: 方案基于 P3 框架或 PROCEED 框架
- **评估指标**: 提供可量化的评估指标

### 模型特点

- **Base Model**: Qwen/Qwen3-VL-4B-Instruct
- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
- **Language**: 中文 (Chinese)
- **Domain**: Healthcare, Health Recommendation

## Model Details

### Model Description

- **Developed by:** oscarzhang
- **Model type:** LoRA Adapter for Qwen3-VL-4B-Instruct
- **Language(s):** Chinese (中文)
- **License:** Apache 2.0 (inherited from base model)
- **Finetuned from:** Qwen/Qwen3-VL-4B-Instruct

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

这个模型可以直接用于生成健康干预方案。用户需要提供：
- 粗症状（主要症状描述）
- 细化症状（具体症状细节）

模型将输出包含以下内容的干预方案：
1. **推荐干预**：
   - 生活方式：具体的行动建议
   - 心理：心理认知层面的干预
   - 环境：环境改造建议
2. **评估指标**：可量化测量的指标

### 使用示例

```python
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer

# 加载基础模型和适配器
base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3-VL-4B-Instruct",
    trust_remote_code=True
)
model = PeftModel.from_pretrained(base_model, "oscarzhang/HealthRecommendation")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-VL-4B-Instruct", trust_remote_code=True)

# 生成干预方案
prompt = """请基于症状信息，生成个性化的健康干预方案。

粗症状：疲劳
细化症状：早晨起床后持续疲惫感，影响日常工作"""
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=500, temperature=0.3)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
```

### Downstream Use

这个模型可以进一步微调用于：
- 特定疾病的干预方案生成
- 不同年龄段人群的健康建议
- 结合更多健康数据的推荐系统

### Out-of-Scope Use

⚠️ **重要限制**：
- 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

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

## How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

## Training Details

### Training Data

训练数据包含126个健康干预方案样本，每个样本包含：
- 症状信息（粗症状和细化症状）
- 理论框架分析（P3框架和PROCEED框架）
- 完整的干预方案（生活方式、心理、环境三个维度）
- 评估指标

### Training Procedure

#### Preprocessing

训练数据经过以下预处理：
- 症状标准化
- 理论框架提取
- 干预方案结构化
- 质量评分验证

#### Training Hyperparameters

- **Training method**: LoRA (Low-Rank Adaptation)
- **Training regime**: fp16 mixed precision
- **LoRA rank (r)**: 16
- **LoRA alpha**: 16
- **LoRA dropout**: 0.05
- **Target modules**: v_proj, q_proj, k_proj, o_proj
- **Learning rate**: 2e-4 (with linear decay and warmup)
- **Batch size**: 1 (with gradient accumulation of 8)
- **Training steps**: 100
- **Max sequence length**: 512 tokens

#### Training Results

- **Initial Loss**: 2.5
- **Final Loss**: 0.7
- **Loss reduction**: 72%
- **Training time**: ~1.7 hours

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

#### Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

#### Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

### Results

[More Information Needed]

#### Summary



## Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]

## Technical Specifications [optional]

### Model Architecture and Objective

[More Information Needed]

### Compute Infrastructure

[More Information Needed]

#### Hardware

[More Information Needed]

#### Software

[More Information Needed]

## Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

[More Information Needed]

**APA:**

[More Information Needed]

## Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

## More Information [optional]

[More Information Needed]

## Model Card Authors [optional]

[More Information Needed]

## Model Card Contact

[More Information Needed]
### Framework versions

- PEFT 0.17.1