Hugging Face's logo

medmekk
/
Llama-3.1-8B-Instruct-torchao-int8da8w

PyTorch
llama
torchao
Model card Files Community
Llama-3.1-8B-Instruct-torchao-int8da8w / README.md
medmekk's picture
medmekk HF staff
Upload folder using huggingface_hub
74f15ac verified
preview code
|
raw
history blame contribute delete
687 Bytes
metadata
base_model:
  - medmekk/Llama-3.1-8B-Instruct-torchao-int8da8w

medmekk/Llama-3.1-8B-Instruct-torchao-int8da8w (Quantized)

Description

This model is a quantized version of the original model medmekk/Llama-3.1-8B-Instruct-torchao-int8da8w. 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("medmekk/Llama-3.1-8B-Instruct-torchao-int8da8w")