PMC LLAMA 7B

🚀 PMC_LLAMA_7B

This repository hosts PMC_LLAMA_7B, a model derived from fine - tuning LLaMA - 7b on PMC papers in the S2ORC dataset, offering potential in medical - related applications.

🚀 Quick Start

This repo contains PMC_LLAMA_7B, which is LLaMA - 7b finetuned on the PMC papers in S2ORC dataset.

✨ Features

• The model was trained on the PMC papers in the S2ORC dataset, which is beneficial for medical - related tasks.
• Specific hyperparameters were used during training to optimize the model's performance.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

import transformers
import torch
tokenizer = transformers.LlamaTokenizer.from_pretrained('chaoyi-wu/PMC_LLAMA_7B')
model = transformers.LlamaForCausalLM.from_pretrained('chaoyi-wu/PMC_LLAMA_7B')
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:

• Epochs: 5
• Batch size: 128
• Cutoff length: 512
• Learning rate: 2e - 5

Each epoch we sample 512 tokens per paper for training.

📄 License

The model is released under the Apache - 2.0 license.