README.md

---
language: en
license: apache-2.0
base_model: unsloth/Qwen3-4B-Thinking-2507
tags:
- medical
- llm
- qwen3
- thinking-model
- entity-extraction
- relation-extraction
- lora
- peft
library_name: transformers
pipeline_tag: text-generation
---

# Medical-NER-Qwen-4B-Thinking

## Model Description

This is a fine-tuned medical LLM based on Qwen3-4B-Thinking, specialized for medical entity and relationship extraction.

## Model Details

- **Base Model**: unsloth/Qwen3-4B-Thinking-2507
- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
- **Domain**: Medical Literature Analysis
- **Tasks**: Entity Recognition, Relationship Extraction
- **Language**: English

## Performance Metrics

| Metric | Entity Extraction | Relationship Extraction |
|--------|------------------|------------------------|
| Precision | 0.000 | 0.000 |
| Recall | 0.000 | 0.000 |
| F1-Score | 0.000 | 0.000 |

## Usage

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

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-3B-Thinking",
    torch_dtype="auto",
    device_map="auto"
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "xingqiang/Medical-NER-Qwen-4B-Thinking")
tokenizer = AutoTokenizer.from_pretrained("xingqiang/Medical-NER-Qwen-4B-Thinking")

# Generate medical analysis
text = "Hepatitis C virus causes chronic liver infection."
messages = [
    {"role": "user", "content": f"Extract medical entities and relationships from: {text}"}
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
```