You can deploy this model and start earning money today!

jerryzh168/
Meta-Llama-3-8B-torchao-int4_weight_only-gs_128

Name: Meta-Llama-3-8B-torchao-int4_weight_only-gs_128
Availability: InStock

pytorch

llama

jerryzh168/Meta-Llama-3-8B-torchao-int4_weight_only-gs_128

quantized

torchao

Views

No views yet

jerryzh168/Meta-Llama-3-8B-torchao-int4_weight_only-gs_128 (Quantized)

Description

This model is a quantized version of the original model jerryzh168/Meta-Llama-3-8B-torchao-int4_weight_only-gs_128. It has been quantized using int4_weight_only quantization with torchao.

Quantization Details

Quantization Type: int4_weight_only
Group Size: 128

Usage

You can use this model in your applications by loading it directly from the Hugging Face Hub:

python

from transformers import AutoModel

model = AutoModel.from_pretrained("jerryzh168/Meta-Llama-3-8B-torchao-int4_weight_only-gs_128")