AutoRound-INT4-gs128
Collection
A collection of models quantized in AutoRound format using Intel AutoRound, INT4, groupsize 128
•
69 items
•
Updated
Quantized version of EleutherAI/pythia-410m using torch.float32 for quantization tuning.
Fast and low memory, 2-3X speedup (slight accuracy drop at W4G128)
Quantization framework: Intel AutoRound
Note: this INT4 version of pythia-410m has been quantized to run inference through CPU.
I suggest to install requirements into a dedicated python-virtualenv or a conda enviroment.
python -m pip install <package> --upgrade
python -m pip install git+https://github.com/intel/auto-round.git
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "EleutherAI/pythia-410m"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
from auto_round import AutoRound
bits, group_size, sym = 4, 128, True
autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym)
autoround.quantize()
output_dir = "./AutoRound/EleutherAI_pythia-410m-autoround-int4-gs128-sym"
autoround.save_quantized(output_dir, format='auto_round', inplace=True)
This quantized model comes with no warrenty. It has been developed only for research purposes.
Base model
EleutherAI/pythia-410m