Edit model card

INT8 MiniLM finetuned MRPC


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

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

Collection including Intel/MiniLM-L12-H384-uncased-mrpc-int8-qat-inc