iproskurina/Llama-3.1-8B-Instruct-gptqmodel-4bit-g32

Llama-3.1-8B-Instruct - GPTQ (4-bit)

Source model: meta-llama/Llama-3.1-8B-Instruct

This model was quantized to 4-bit using GPTQModel.

Quantization parameters:

• bits: 4
• group_size: 32
• damp_percent: 0.05
• desc_act: False

Usage

# pip install transformers gptqmodel --no-build-isolation
from gptqmodel import GPTQModel
model_id = "iproskurina/Llama-3.1-8B-Instruct-gptqmodel-4bit-g32"
model = GPTQModel.load(model_id)
result = model.generate("Uncovering deep insights")[0]
print(model.tokenizer.decode(result))