smpanaro/pythia-410m-AutoGPTQ-4bit-128g

pythia-410m quantized to 4-bit using AutoGPTQ.

To use, first install AutoGPTQ:

pip install auto-gptq

Then load the model from the hub:

from transformers import AutoModelForCausalLM, AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig

model_name = "smpanaro/pythia-410m-AutoGPTQ-4bit-128g"
model = AutoGPTQForCausalLM.from_quantized(model_name)

Model	4-Bit Perplexity	16-Bit Perplexity	Delta
smpanaro/pythia-160m-AutoGPTQ-4bit-128g	33.4375	23.3024	10.1351
smpanaro/pythia-410m-AutoGPTQ-4bit-128g	21.4688	13.9838	7.485

_{Wikitext perplexity measured as in the huggingface docs, lower is better}