MiniLM
Collection
Fine-tuned version of Microsoft's MiniLM models, trained on the GLUE MRPC dataset.
•
5 items
•
Updated
INT8 MiniLM 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/MiniLM-L12-H384-uncased-mrpc.
Test result
| INT8 | FP32 | |
|---|---|---|
| Accuracy (eval-f1) | 0.9068 | 0.9097 |
| Model size (MB) | 33.1 | 127 |
Load with optimum:
from optimum.intel import INCModelForSequenceClassification
model_id = "Intel/MiniLM-L12-H384-uncased-mrpc-int8-qat"
int8_model = INCModelForSequenceClassification(model_id)
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
- train_batch_size: 16
- eval_batch_size: 8
- Downloads last month
- 5
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.