HF-Quantization/Llama-3.2-1B-BNB-INT8

meta-llama/Llama-3.2-1B (Quantized)

Description

This model is a quantized version of the original model meta-llama/Llama-3.2-1B. It was quantized using Bitsandbytes.

Quantization Details

• Quantization Parameters: BitsAndBytesConfig(load_in_8bit=True)

Usage

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

In order to run the inference with Llama-3.2-1B-BNB-INT8, torch andbitsandbytes need to be installed as:

pip install torch bitsandbytes --upgrade

Then, preferably the latest version of transformers need to be installed, as:

pip install transformers[accelerate] --upgrade

To run the inference the model can be instantiated as any other causal language modeling model via AutoModelForCausalLM and run the inference normally.

from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Llama-3.2-1B-BNB-INT8")