metadata
language:
- en
- es
- fr
- de
- pt
- ja
- it
- zh
- ko
- ar
- cs
- nl
pipeline_tag: text-generation
license: apache-2.0
library_name: transformers
tags:
- granite-3.2
- autoround
- auto-round
- intel-autoround
- intel
- awq
- auto-awq
- autoawq
- woq
- pytorch
- ibm
- granite
- granite-3
model_name: Granite 3.2 2b instruct
base_model:
- ibm-granite/granite-3.2-2b-instruct
inference: false
model_creator: ibm-granite
prompt_template: '{prompt}'
quantized_by: fbaldassarri
Model Information
Quantized version of ibm-granite/granite-3.2-2b-instruct using torch.float32 for quantization tuning.
- 4 bits (INT4)
- group size = 128
- Asymmetrical Quantization
- Method AutoAWQ format
Quantization framework: Intel AutoRound v0.4.7
Note: this INT4 version of granite-3.2-2b-instruct 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/v0.4.7.tar.gz
tar -xvzf v0.4.7.tar.gz
cd auto-round-0.4.7
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 = "ibm-granite/granite-3.2-2b-instruct"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
from auto_round import AutoRound
bits, group_size, sym, device = 4, 128, False, 'cpu'
autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym, device=device)
autoround.quantize()
output_dir = "./AutoRound/ibm-granite_granite-3.2-2b-instruct-autoawq-int4-gs128-asym"
autoround.save_quantized(output_dir, format='auto_awq', inplace=True)
License
Disclaimer
This quantized model comes with no warrenty. It has been developed only for research purposes.