license: mit
language:
- en
metrics:
- f1
tags:
- medical
MentaLLaMA-chat-13B
MentaLLaMA-chat-13B is part of the MentaLLaMA project, the first open-source large language model (LLM) series for interpretable mental health analysis with instruction-following capability. The model is expected to make complex mental health analyses for various mental health conditions and give reliable explanations for each of its predictions. It is fine-tuned on the IMHI dataset with 75K high-quality natural language instructions to boost its performance in downstream tasks. We perform a comprehensive evaluation on the IMHI benchmark with 20K test samples. The result shows that MentalLLaMA approaches state-of-the-art discriminative methods in correctness and generates high-quality explanations.
Other Models in MentaLLaMA
In addition to MentaLLaMA-chat-13B, the MentaLLaMA project includes another model: MentaLLaMA-chat-7B, MentalBART, MentalT5.
MentaLLaMA-chat-7B: This model
MentalBART: This model
MentalT5: This model
Usage
You can use the MentaLLaMA-chat-13B model in your Python project with the Hugging Face Transformers library. Here is a simple example of how to load the model:
from transformers import LlamaTokenizer, LlamaForCausalLM
tokenizer = LlamaTokenizer.from_pretrained('klyang/MentaLLaMA-chat-13B')
model = LlamaForCausalLM.from_pretrained('klyang/MentaLLaMA-chat-13B', device_map='auto')
In this example, LlamaTokenizer is used to load the tokenizer, and LlamaForCausalLM is used to load the model. The device_map='auto' argument is used to automatically
use the GPU if it's available.
License
MentaLLaMA-chat-13B is licensed under MIT. For more details, please see the MIT file.
About
This model is part of the MentaLLaMA project. For more information, you can visit the MentaLLaMA project on GitHub.
Citation
If you use MentaLLaMA-chat-7B in your work, please cite our paper:
@misc{yang2023mentalllama,
title={MentalLLaMA: Interpretable Mental Health Analysis on Social Media with Large Language Models},
author={Kailai Yang and Tianlin Zhang and Ziyan Kuang and Qianqian Xie and Sophia Ananiadou},
year={2023},
eprint={2309.13567},
archivePrefix={arXiv},
primaryClass={cs.CL}
}