Modelpublic

macadeliccc/LiberatedHermes-2-Pro-Mistral-7B-HQQ

sourceHugging Faceupdated 3y agoView on Hugging Face

0likes15downloads

Model Card

LiberatedHermes-2-Pro-Mistral-7B-HQQ

This is a 4bit quantization using HQQ

Load Script

python

from hqq.engine.hf import HQQModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(model_id)
model     = HQQModelForCausalLM.from_quantized(model_id)