Downloads · 30 days
14
18% of all-time downloads
fbaldassarri/ibm-granite_granite-3.2-2b-instruct-autoround-int8-gs128-sym
ibm-granite_granite-3.2-2b-instruct-autoround-int8-gs128-sym is a text generation model from fbaldassarri. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Quantized version of ibm-granite/granite-3.2-2b-instruct using torch.float32 for quantization tuning. - 8 bits (INT8) - group size = 128 - Symmetrical Quantization - Method WoQ (AutoRound format)
Downloads · 30 days
14
18% of all-time downloads
All-time downloads
77
Public
Parameters
734M
2.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.9 GB · 100%
How the weights are stored.
I32614M · 84%
From the Hugging Face model README
Quantized version of ibm-granite/granite-3.2-2b-instruct using torch.float32 for quantization tuning.
Fast and low memory, 2-3X speedup (slight accuracy drop at W8G128)
Quantization framework: Intel AutoRound v0.4.7
Note: this INT8 version of granite-3.2-2b-instruct has been quantized to run inference through CPU.
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
pip install -vvv --no-build-isolation -e .[cpu]
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 = 8, 128, True, '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-autoround-int8-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.