Quokka-13b-base

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

This model is optimized for Material Science by continuing pertaining on over 1 million Material science academic articles based on LLaMa-2-13b.

• Developed by: [UCSB]

• Language(s) (NLP): [More Information Needed]

• License: [More Information Needed]

• Finetuned from model [optional]: [LLaMa-2]

• Paper [optional]: [https://arxiv.org/pdf/2401.01089.pdf]

• Demo [optional]: [More Information Needed]

How to Get Started with the Model

from transformers import LlamaTokenizer, LlamaForCausalLM
import torch

tokenizer = LlamaTokenizer.from_pretrained("Xianjun/Quokka-13b-base")
model = LlamaForCausalLM.from_pretrained("Xianjun/Quokka-13b-base").half().to("cuda")

instruction = "How to ..."
batch = tokenizer(instruction, return_tensors="pt", add_special_tokens=False).to("cuda")
with torch.no_grad():
    output = model.generate(**batch, max_new_tokens=512, temperature=0.7, do_sample=True)
    response = tokenizer.decode(output[0], skip_special_tokens=True)

Citation

If you find Quokka useful in your research, please cite the following paper:

@inproceedings{Yang2024QuokkaAO,
  title={Quokka: An Open-source Large Language Model ChatBot for Material Science},
  author={Xianjun Yang and Stephen Wilson and Linda Ruth Petzold},
  year={2024},
  url={https://api.semanticscholar.org/CorpusID:266725577}
}