Downloads · 30 days
32
5% of all-time downloads
bert-base-uncased-CoLA-int8-inc
Intel/bert-base-uncased-CoLA-int8-inc
bert-base-uncased-CoLA-int8-inc is a text classification model from Intel. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
This is an INT8 PyTorch model quantized with huggingface/optimum-intel through the usage of Intel® Neural Compressor.
All-time downloads
626
Public
Repo size
112 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin112 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- May 11, 2023
- Updated
- Mar 22, 2024
- SHA
- e6929d56
Try a prompt
Model card
From the Hugging Face model README
INT8 BERT base uncased finetuned CoLA
Post-training static quantization
PyTorch
This is an INT8 PyTorch model quantized with huggingface/optimum-intel through the usage of Intel® Neural Compressor.
The original fp32 model comes from the fine-tuned model textattack/bert-base-uncased-CoLA.
Test result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-f1) | 0.5451 | 0.5339 |
| Model size (MB) | 112 | 438 |
Load with optimum:
from optimum.intel import INCModelForSequenceClassification
model_id = "Intel/bert-base-uncased-CoLA-int8"
int8_model = INCModelForSequenceClassification.from_pretrained(model_id)
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- mit
- Languages
- en
- Created
- May 11, 2023
- Updated
- Mar 22, 2024