irresistiblegrace97/TinyLlama-1.1B-Chat-v1.0-torchao-int4_weight_only-gs_4096 (Quantized)

Description

This model is a quantized version of the original model irresistiblegrace97/TinyLlama-1.1B-Chat-v1.0-torchao-int4_weight_only-gs_4096. It has been quantized using int4_weight_only quantization with torchao.

Quantization Details

• Quantization Type: int4_weight_only
• Group Size: 4096

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("irresistiblegrace97/TinyLlama-1.1B-Chat-v1.0-torchao-int4_weight_only-gs_4096")