You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

You agree to not use the model to conduct experiments that cause harm to human subjects.

Log in or Sign Up to review the conditions and access this model content.

Model Card for Model ID

VaxLLM (Vaccine Large Language Model) is a fine-tuned Llama-3 model to automatically perform the classification and annotation of vaccine-related articles, using Brucella vaccines as a case study.

Model Details

Model Description

VaxLLM can classify the articles to filter the relevant articles containing specific information about the Brucella vaccine.

VaxLLM can also systematically extract the key information about vaccines, including the vaccine antigen, vaccine formulation, vaccine platform, host species used as animal models, and experiments used to investigate the vaccine.

  • Developed by: Xingxian Li at He Group, University of Michigan
  • License: MIT
  • Finetuned from model: Meta-Llama-3-8B-Instruct
  • Task Supported: Text Generation
  • Specialized Domain: Brucella vaccine-related content
  • Model Type: Fine-tuned Language Model

Model Sources

Uses

  • Use case: To assist researchers in identifying and analyzing Brucella vaccine-related articles for research and development. -Intended Users: Researchers, bioinformaticians, and professionals in the field of vaccine development.

Direct Use

Gated model: Login with an HF token with gated access permission, please request permission before usage

huggingface-cli login

Use a pipeline as a high-level helper

from transformers import pipeline
pipe = pipeline("question-answering", model="Xingxian123/VaxLLM")

Use directly

from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Xingxian123/VaxLLM")
model = AutoModelForCausalLM.from_pretrained("Xingxian123/VaxLLM")

prompt

classification: Using the following data: '{Abstract information}', is this article about a brucella vaccine? To classify an article as being about a brucella vaccine, you must successfully extract at least some information about the vaccine formulation. This includes details such as the antigen, protein, gene, adjuvant, or vaccine platform mentioned in the abstract.

annotation: Extract the following details using the given data: '{Abstract information}': Vaccine Introduction,Vaccine Antigen, Vaccine Type, Vaccine Formulation, Host Species Used as Laboratory Animal Model, Experiment Used to investigate the vaccine Ensure each response is based solely on the provided data. Ensure the response is formatted as follows: Response: Vaccine Introduction: Vaccine Type: Vaccine Antigen: Vaccine Formulation: Host Species Used as Laboratory Animal Model: Experiment Used to investigate the vaccine:

Bias, Risks, and Limitations

While the model has been fine-tuned for Brucella vaccine-related tasks, users should carefully validate outputs, particularly for critical applications. Model might struggle with content outside the Brucella vaccine domain.

Recommendations

Users should be made aware of the risks, biases and limitations of the model.

Model Card Contact

xingxian@umich.edu

Downloads last month
10
Safetensors
Model size
8.03B params
Tensor type
BF16
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Xingxian123/VaxLLM

Finetuned
(523)
this model