|
|
--- |
|
|
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-3.3 |
|
|
- autoround |
|
|
- auto-round |
|
|
- intel-autoround |
|
|
- intel |
|
|
- woq |
|
|
- pytorch |
|
|
- ibm |
|
|
- granite |
|
|
- granite-3 |
|
|
model_name: Granite 3.3 2b instruct |
|
|
base_model: |
|
|
- ibm-granite/granite-3.3-2b-instruct |
|
|
inference: false |
|
|
model_creator: ibm-granite |
|
|
prompt_template: '{prompt}' |
|
|
quantized_by: fbaldassarri |
|
|
--- |
|
|
|
|
|
## Model Information |
|
|
|
|
|
Quantized version of [ibm-granite/granite-3.3-2b-instruct](https://huggingface.co/fbaldassarri/ibm-granite/granite-3.3-2b-instruct) using torch.float32 for quantization tuning. |
|
|
- 8 bits (INT8) |
|
|
- group size = 128 |
|
|
- Asymmetrical Quantization |
|
|
- Method WoQ (AutoRound format) |
|
|
|
|
|
Fast and low memory, 2-3X speedup (slight accuracy drop at W8G128) |
|
|
|
|
|
Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.7 |
|
|
|
|
|
Note: this INT8 version of granite-3.3-2b-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-3.3-2b-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, 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-3.3-2b-instruct-autoround-int8-gs128-asym" |
|
|
autoround.save_quantized(output_dir, format='auto_round', inplace=True) |
|
|
``` |
|
|
|
|
|
## License |
|
|
|
|
|
[Apache 2.0 License](https://choosealicense.com/licenses/apache-2.0/) |
|
|
|
|
|
## Disclaimer |
|
|
|
|
|
This quantized model comes with no warrenty. It has been developed only for research purposes. |
|
|
|
