Llama3 8B Medical

🚀 医疗-Llama3-8B-4bit：针对医疗问答微调的Llama3模型

本项目是基于LLAMA-3-8B的医疗微调版本，使用常见的开源数据集将其量化为4位。在多语言任务上表现出了显著的提升。采用了标准的比特量化技术进行微调后量化，降低了运行模型所需的计算时间复杂度和空间复杂度。整体架构完全基于LLAMA-3。

本仓库提供了强大的Llama3 8B模型的微调版本，专门设计用于以信息丰富的方式回答医疗问题。它利用了AI医疗聊天机器人数据集（ruslanmv/ai-medical-chatbot）中包含的丰富知识。

🚀 快速开始

本仓库提供了强大的Llama3 8B模型的微调版本，专门设计用于以信息丰富的方式回答医疗问题。它利用了AI医疗聊天机器人数据集（ruslanmv/ai-medical-chatbot）中包含的丰富知识。

✨ 主要特性

• 专注医疗领域：针对健康相关的询问进行了优化。
• 知识储备丰富：在全面的医疗聊天机器人数据集上进行训练。
• 文本生成能力：生成信息丰富且可能有帮助的回复。

📦 安装指南

该模型可通过Hugging Face Transformers库访问。使用pip进行安装：

pip install git+https://github.com/huggingface/accelerate.git
pip install git+https://github.com/huggingface/transformers.git
pip install  bitsandbytes

💻 使用示例

基础用法

以下是一个Python代码片段，展示了如何与llama3-8B-medical模型进行交互，并生成医疗问题的答案：

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import torch

# Load tokenizer and model
model_id = "ruslanmv/llama3-8B-medical"

quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.bfloat16
)

tokenizer = AutoTokenizer.from_pretrained(model_id)
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

model = AutoModelForCausalLM.from_pretrained(model_id, config=quantization_config)

def create_prompt(user_query):
  B_INST, E_INST = "<s>[INST]", "[/INST]"
  B_SYS, E_SYS = "<<SYS>>\n", "\n<</SYS>>\n\n"
  DEFAULT_SYSTEM_PROMPT = """\
  You are an AI Medical Chatbot Assistant, provide comprehensive and informative responses to your inquiries.
  If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."""
  SYSTEM_PROMPT = B_SYS + DEFAULT_SYSTEM_PROMPT + E_SYS
  instruction = f"User asks: {user_query}\n"
  prompt = B_INST + SYSTEM_PROMPT + instruction + E_INST
  return prompt.strip()

def generate_text(model, tokenizer, prompt,
                  max_length=200,
                  temperature=0.8,
                  num_return_sequences=1):
    prompt = create_prompt(user_query)
    # Tokenize the prompt
    input_ids = tokenizer.encode(prompt, return_tensors="pt").to(device)  # Move input_ids to the same device as the model
    # Generate text
    output = model.generate(
        input_ids=input_ids,
        max_length=max_length,
        temperature=temperature,
        num_return_sequences=num_return_sequences,
        pad_token_id=tokenizer.eos_token_id,  # Set pad token to end of sequence token
        do_sample=True
    )    
    # Decode the generated output
    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
  
   # Split the generated text based on the prompt and take the portion after it
    generated_text = generated_text.split(prompt)[-1].strip()

    return generated_text
# Example usage
# - Context: First describe your problem.
# - Question: Then make the question.
user_query = "I'm a 35-year-old male experiencing symptoms like fatigue, increased sensitivity to cold, and dry, itchy skin. Could these be indicative of hypothyroidism?"
generated_text = generate_text(model, tokenizer, user_query)    
print(generated_text)

回答类型如下：

Yes, it is possible. Hypothyroidism can present symptoms like increased sensitivity to cold, dry skin, and fatigue. These symptoms are characteristic of hypothyroidism. I recommend consulting with a healthcare provider. 2. Hypothyroidism can present symptoms like fever, increased sensitivity to cold, dry skin, and fatigue. These symptoms are characteristic of hypothyroidism. 

📚 详细文档

模型与开发

• 开发者：ruslanmv
• 许可证：Apache-2.0
• 微调基础模型：meta-llama/Meta-Llama-3-8B

重要提示

⚠️ 重要提示

该模型仅用于信息参考，不能替代专业的医疗建议。如有任何医疗问题，请始终咨询合格的医疗保健提供者。

免责声明

💡 使用建议

虽然我们努力提供信息丰富的回复，但不能保证模型输出的准确性。因此，如需明确的医疗建议，务必咨询医生或其他医疗专业人员。

📄 许可证

该模型根据Apache许可证2.0进行分发（详情请参阅LICENSE文件）。

贡献

我们欢迎对本仓库进行贡献！如果您有改进建议或优化方案，请随时创建拉取请求。