Downloads · 30 days
12
2% of all-time downloads
albert-base-v2-sst2-int8-dynamic-inc
INC4AI/albert-base-v2-sst2-int8-dynamic-inc
albert-base-v2-sst2-int8-dynamic-inc is a text classification model from INC4AI. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
This is an INT8 ONNX model quantized with Intel® Neural Compressor.
All-time downloads
616
Public
Repo size
121 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx61.6 MB · 96%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- albert
- Access
- Public
- Created
- Dec 28, 2022
- Updated
- Jun 27, 2023
- SHA
- cf5ceed5
Try a prompt
Datasets
Model card
From the Hugging Face model README
INT8 albert-base-v2-sst2
Post-training dynamic quantization
ONNX
This is an INT8 ONNX model quantized with Intel® Neural Compressor.
The original fp32 model comes from the fine-tuned model Alireza1044/albert-base-v2-sst2.
Test result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-accuracy) | 0.9186 | 0.9232 |
| Model size (MB) | 59 | 45 |
Load ONNX model:
from optimum.onnxruntime import ORTModelForSequenceClassification
model = ORTModelForSequenceClassification.from_pretrained('Intel/albert-base-v2-sst2-int8-dynamic')
- Task
- Text Classification
- Library
- transformers
- Type
- albert
- License
- apache-2.0
- Languages
- en
- Created
- Dec 28, 2022
- Updated
- Jun 27, 2023