metadata
language:
- en
tags:
- pytorch
- causal-lm
- pythia
- autoround
- intel-autoround
- auto-round
- intel
- woq
- gptq
- auto-gptq
- autogptq
- eleutheraI
license: apache-2.0
model_name: Pythia 2.8b
base_model: EleutherAI/pythia-2.8b
inference: false
model_creator: EleutherAI
datasets:
- EleutherAI/pile
pipeline_tag: text-generation
prompt_template: '{prompt} '
quantized_by: fbaldassarri
Model Information
Quantized version of EleutherAI/pythia-2.8b using torch.float32 for quantization tuning.
- 8 bits (INT8)
- group size = 64
- Asymmetrical Quantization
- Method WoQ: GPTQ (AutoGPTQ algorithm)
Quantization framework: Intel AutoRound v0.5.1
Note: this INT8 version of pythia-2.8b has been quantized to run inference through CPU.
Replication Recipe
Step 1 Install Requirements
I suggest to install requirements into a dedicated python-virtualenv or a conda enviroment.
wget https://github.com/intel/auto-round/archive/refs/tags/v0.5.1.tar.gz
tar -xvzf v0.5.1.tar.gz
cd auto-round-0.5.1
pip install -r requirements-cpu.txt --upgrade
Step 2 Build Intel AutoRound wheel from sources
pip install -vvv --no-build-isolation -e .[cpu]
Step 3 Script for Quantization
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "EleutherAI/pythia-2.8b"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
from auto_round import AutoRound
bits, group_size, sym, device, amp = 8, 64, False, 'cpu', False
autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym, device=device, amp=amp)
autoround.quantize()
output_dir = "./AutoRound/EleutherAI_pythia-2.8b-autogptq-int8-gs64-asym"
autoround.save_quantized(output_dir, format='auto_gptq', inplace=True)
License
Disclaimer
This quantized model comes with no warrenty. It has been developed only for research purposes.