Medguanaco 65b GPTQ

🚀 Medguanaco 65b

A large language model LoRA specifically fine - tuned for medical domain tasks, aiming to improve question - answering and medical dialogue.

🚀 Quick Start

The Medguanaco 65b model is designed for medical domain tasks. Here are the steps to load this model:

# Some llama or alpaca model 65b
base_model = "nmitchko/medguanaco-65b-GPTQ"
model = LlamaForCausalLM.from_pretrained(
    base_model,    
    load_in_8bit=load_8bit,
    torch_dtype=torch.float16
)

✨ Features

• Specifically fine - tuned for medical domain tasks, improving question - answering and medical dialogue.
• Based on the Guanaco LORA of LLaMA with 65B parameters.
• Trained using LoRA and reduced to 8bit to reduce memory footprint.

📚 Documentation

Architecture

nmitchko/medguanaco-65b-GPTQ is a large language model LoRA specifically fine - tuned for medical domain tasks. It is based on the Guanaco LORA of LLaMA weighing in at 65B parameters. The primary goal of this model is to improve question - answering and medical dialogue tasks. It was trained using LoRA and reduced to 8bit, to reduce memory footprint.

Training Data

The training data for this project was sourced from various resources. Firstly, we used Anki flashcards to automatically generate questions from the front of the cards and answers from the back of the card. Secondly, we generated medical question - answer pairs from Wikidoc. We extracted paragraphs with relevant headings, and used Chat - GPT 3.5 to generate questions from the headings and using the corresponding paragraphs as answers. This dataset is still under development and we believe that approximately 70% of these question answer pairs are factual correct. Thirdly, we used StackExchange to extract question - answer pairs, taking the top - rated question from five categories: Academia, Bioinformatics, Biology, Fitness, and Health. Additionally, we used a dataset from ChatDoctor consisting of 200,000 question - answer pairs, available at https://github.com/Kent0n - Li/ChatDoctor.

🔧 Technical Details

The model is based on the Guanaco LORA of LLaMA with 65B parameters. It uses the LoRA technique for training and is reduced to 8bit to save memory. The training data is a combination of data from Anki flashcards, Wikidoc, StackExchange, and ChatDoctor.

📄 License

The model is licensed under CC.

⚠️ Important Note

The model may not perform effectively outside the scope of the medical domain. The training data primarily targets the knowledge level of medical students, which may result in limitations when addressing the needs of board - certified physicians. The model has not been tested in real - world applications, so its efficacy and accuracy are currently unknown. It should never be used as a substitute for a doctor's opinion and must be treated as a research tool only.