Downloads · 30 days
29
1% of all-time downloads
bert-base-uncased-mrpc-int8-qat-inc
INC4AI/bert-base-uncased-mrpc-int8-qat-inc
bert-base-uncased-mrpc-int8-qat-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 PyTorch model quantized with huggingface/optimum-intel through the usage of Intel® Neural Compressor.
All-time downloads
3.1K
Public
Repo size
406 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin112 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Apr 6, 2022
- Updated
- Mar 21, 2024
- SHA
- e916825d
Try a prompt
Datasets
Model card
From the Hugging Face model README
INT8 BERT base uncased finetuned MRPC
QuantizationAwareTraining
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 Intel/bert-base-uncased-mrpc.
Test result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-f1) | 0.9142 | 0.9042 |
| Model size (MB) | 107 | 418 |
Load with optimum:
from optimum.intel import INCModelForSequenceClassification
model_id = "Intel/bert-base-uncased-mrpc-int8-qat"
int8_model = INCModelForSequenceClassification.from_pretrained(model_id)
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
- train_batch_size: 8
- eval_batch_size: 8
- eval_steps: 100
- load_best_model_at_end: True
- metric_for_best_model: f1
- early_stopping_patience = 6
- early_stopping_threshold = 0.001
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Languages
- en
- Created
- Apr 6, 2022
- Updated
- Mar 21, 2024