Meta-Llama-3-8B-Instruct-GPTQ/README.md

license_name, tags, model_name, base_model, inference, model_creator, pipeline_tag, quantized_by

license_name	tags	model_name	base_model	inference	model_creator	pipeline_tag	quantized_by
llama3	finetuned quantized 4-bit gptq transformers safetensors llama text-generation facebook meta pytorch llama-3 conversational en license:other autotrain_compatible endpoints_compatible has_space text-generation-inference region:us	Meta-Llama-3-8B-Instruct-GPTQ	meta-llama/Meta-Llama-3-8B-Instruct	false	meta-llama	text-generation	MaziyarPanahi

Description

MaziyarPanahi/Meta-Llama-3-8B-Instruct-GPTQ is a quantized (GPTQ) version of meta-llama/Meta-Llama-3-8B-Instruct

How to use

Install the necessary packages

pip install --upgrade accelerate auto-gptq transformers

Example Python code

from transformers import AutoTokenizer, pipeline
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import torch

model_id = "MaziyarPanahi/Meta-Llama-3-8B-Instruct-GPTQ"

quantize_config = BaseQuantizeConfig(
        bits=4,
        group_size=128,
        desc_act=False
    )

model = AutoGPTQForCausalLM.from_quantized(
        model_id,
        use_safetensors=True,
        device="cuda:0",
        quantize_config=quantize_config)

tokenizer = AutoTokenizer.from_pretrained(model_id)

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.95,
    repetition_penalty=1.1
)

outputs = pipe("What is a large language model?")
print(outputs[0]["generated_text"])