Modelpublic

matsci-llm-anon/Mistral-ft-Combined

sourceHugging Facecc-by-4.0updated 27d agoView on Hugging Face

0likes13downloads

Model Card

Mistral-ft-Combined

LoRA adapter for multi-task training across the materials tasks.

Released for double-blind review of How Large Language Models Learn Materials Science.


Base model	`mistralai/Mistral-7B-Instruct-v0.2`
PEFT type	LoRA (r=8, alpha=16, dropout=0.05)
Target modules	`v_proj`, `q_proj`

Usage

python

from peft import PeftModel
from transformers import AutoModelForCausalLM
m = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
m = PeftModel.from_pretrained(m, "matsci-llm-anon/Mistral-ft-Combined")

Citation

bibtex

@inproceedings{anonymous2026learn,
  title={How Large Language Models Learn Materials Science},
  author={Anonymous},
  booktitle={Under review},
  year={2026}
}

Author and affiliation information is withheld during double-blind review.