You can deploy this model and start earning money today!

lperng/
medical-model

Name: medical-model
Availability: InStock

Views

No views yet

medical-model

This is a fine-tuned version of the DeepSeek-R1-Distill-Llama-8B model, specifically trained on a medical dataset for enhanced performance in medical question answering and reasoning.

Model Description

Base Model: DeepSeek-R1-Distill-Llama-8B
Fine-tuning Dataset: FreedomIntelligence/medical-o1-reasoning-SFT
Fine-tuning Method: Unsloth's SFTTrainer with LoRA
Language: Chinese

Intended Uses & Limitations

This model is intended for research and educational purposes related to medical question answering. It can provide insightful responses to medical queries, but it is crucial to understand its limitations:

Not a Medical Professional: The model is not a substitute for professional medical advice. Consult with a healthcare provider for any health concerns or before making any decisions based on the model's output.
Potential Biases: The training data may contain biases that could be reflected in the model's responses. Always critically evaluate the information provided.
Limited Scope: The model's knowledge is limited to the information present in its training dataset. It may not be able to answer questions outside its domain of expertise.

How to Use

You can use this model with the following code:

python from unsloth import FastLanguageModel import torch

model, tokenizer = FastLanguageModel.from_pretrained( model_name="lperng/medical-model", load_in_4bit=True, # Optional: Use 4-bit quantization )

prompt = "你的医学问题？" # Replace with your medical question

inputs = tokenizer([prompt], return_tensors="pt").to("cuda") outputs = model.generate(input_ids=inputs.input_ids, attention_mask=inputs.attention_mask) response = tokenizer.batch_decode(outputs)[0]

print(response)

Training and Evaluation Data

This model was trained on the FreedomIntelligence/medical-o1-reasoning-SFT dataset. The dataset contains a collection of medical questions and corresponding answers. Evaluation metrics and results will be added in future updates.

Ethical Considerations

Potential for Misinformation: The model's output should be carefully reviewed to ensure accuracy and prevent the spread of misinformation.
Privacy: When using the model with personal health information, ensure compliance with relevant privacy regulations.
Responsible Use: Use the model responsibly and ethically, considering its potential impact on individuals and society.

Citation

If you use this model in your work, please cite it as follows:

@misc{medical-model, author = {lperng}, title = {medical-model}, year = {2023}, publisher = {Hugging Face}, howpublished = {\url{[redacted link], }

Disclaimer

This model is provided "as is" without warranty of any kind, express or implied. The authors and contributors are not responsible for any damages or liabilities arising from the use of this model.