---
license: mit
datasets:
- yueqingyou/BioQwen
language:
- en
- zh
tags:
- BioQwen
- 0.5B
- Biomedical
- Multi-Tasks
---

# BioQwen: A Small-Parameter, High-Performance Bilingual Model for Biomedical Multi-Tasks

For model inference, please refer to the following example code:

```python
import torch
import transformers
from transformers import AutoTokenizer, AutoModelForCausalLM

transformers.logging.set_verbosity_error()
max_length = 512
model_path = 'yueqingyou/BioQwen-0.5B'
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(model_path, device_map='auto', torch_dtype=torch.bfloat16, attn_implementation='flash_attention_2').eval()

def predict(prompt):
    zh_system = "你是千问生物智能助手，一个专注于生物领域的先进人工智能。"
    en_system = "You are BioQwen, an advanced AI specializing in the field of biology."
    
    english_count, chinese_count = 0, 0
    for char in prompt:
        if '\u4e00' <= char <= '\u9fff':
            chinese_count += 1
        elif 'a' <= char.lower() <= 'z':
            english_count += 1
    lang = 'zh' if chinese_count > english_count else 'en'
    
    messages = [
        {"role": "system", "content": zh_system if lang == 'zh' else en_system},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )

    model_inputs = tokenizer([text], return_tensors="pt").to('cuda')

    with torch.no_grad():
        generated_ids = model.generate(
            model_inputs.input_ids,
            max_new_tokens=max_length,
            eos_token_id=tokenizer.eos_token_id,
            pad_token_id=tokenizer.pad_token_id,
            do_sample=True,
            top_p = 0.9,
            temperature = 0.3,
            repetition_penalty = 1.1
        )

    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]
    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    
    return response.strip()

prompt = 'I am suffering from irregular periods. I am currently taking medication Levothyroxine 50. My T3 is 0.87 ng/mL, T4 is 8.30 ug/dL, TSH is 2.43 uIU/mL. I am 34 years old, weigh 75 kg, and 5 feet tall. Please advice.'
print(f'Question:\t{prompt}\n\nAnswer:\t{predict(prompt)}')

```

For more detailed information and code, please refer to [GitHub](https://github.com/yueqingyou/BioQwen).