metadata
base_model:
- marksaroufim/Meta-Llama-3-8B-torchao-int8_weight_only
marksaroufim/Meta-Llama-3-8B-torchao-int8_weight_only (Quantized)
Description
This model is a quantized version of the original model marksaroufim/Meta-Llama-3-8B-torchao-int8_weight_only. It has been quantized using int8_weight_only quantization with torchao.
Quantization Details
- Quantization Type: int8_weight_only
- Group Size: None
Usage
You can use this model in your applications by loading it directly from the Hugging Face Hub:
from transformers import AutoModel
model = AutoModel.from_pretrained("marksaroufim/Meta-Llama-3-8B-torchao-int8_weight_only")