Downloads · 30 days
16
3% of all-time downloads
distilbert-base-uncased-MRPC-int8-dynamic-inc
Intel/distilbert-base-uncased-MRPC-int8-dynamic-inc
distilbert-base-uncased-MRPC-int8-dynamic-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.
- Model Details - How to Get Started With the Model
All-time downloads
522
Public
Repo size
75.2 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin75.2 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- distilbert
- Access
- Public
- Created
- May 11, 2023
- Updated
- Mar 21, 2024
- SHA
- 48472a70
Try a prompt
Model card
From the Hugging Face model README
Dynamically quantized DistilBERT base uncased finetuned MPRC
Table of Contents
Model Details
Model Description: This model is a DistilBERT fine-tuned on MPRC dynamically quantized with optimum-intel through the usage of huggingface/optimum-intel through the usage of Intel® Neural Compressor.
- Model Type: Text Classification
- Language(s): English
- License: Apache-2.0
- Parent Model: For more details on the original model, we encourage users to check out this model card.
How to Get Started With the Model
PyTorch
To load the quantized model, you can do as follows:
from optimum.intel import INCModelForSequenceClassification
model_id = "Intel/distilbert-base-uncased-MRPC-int8-dynamic"
model = INCModelForSequenceClassification.from_pretrained(model_id)
Test result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-f1) | 0.8983 | 0.9027 |
| Model size (MB) | 75 | 268 |
- Task
- Text Classification
- Library
- transformers
- Type
- distilbert
- License
- mit
- Languages
- en
- Created
- May 11, 2023
- Updated
- Mar 21, 2024