Medllama 13B

🚀 MedLLaMA_13B

This repository houses MedLLaMA_13B, a model achieved by fine - tuning LLaMA - 13B on a medical corpus, tailored for medical - related tasks.

🚀 Quick Start

The model can be loaded as follows:

import transformers
import torch
tokenizer = transformers.LlamaTokenizer.from_pretrained('chaoyi-wu/MedLLaMA_13B')
model = transformers.LlamaForCausalLM.from_pretrained('chaoyi-wu/MedLLaMA_13B')
sentence = 'Hello, doctor' 
batch = tokenizer(
            sentence,
            return_tensors="pt", 
            add_special_tokens=False
        )
with torch.no_grad():
    generated = model.generate(inputs = batch["input_ids"], max_length=200, do_sample=True, top_k=50)
    print('model predict: ',tokenizer.decode(generated[0]))

🔧 Technical Details

The model was trained with the following hyperparameters:

📄 License

This project is licensed under the Apache - 2.0 license.