medmekk/an_other_torchao_dynamic

meta-llama/Meta-Llama-3-8B (Quantized)

Description

This model is a quantized version of the original model meta-llama/Meta-Llama-3-8B. It has been quantized using int8_dynamic_activation_int8_weight quantization with torchao.

Quantization Details

• Quantization Type: int8_dynamic_activation_int8_weight
• 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("meta-llama/Meta-Llama-3-8B")