philschmid / quantized-distilbert-banking77

huggingface.co
Total runs: 5
24-hour runs: 0
7-day runs: 0
30-day runs: -4
Model's Last Updated: June 08 2022
text-classification

Introduction of quantized-distilbert-banking77

Model Details of quantized-distilbert-banking77

Quantized-distilbert-banking77

This model is a statically quantized version of optimum/distilbert-base-uncased-finetuned-banking77 on the banking77 dataset.

The model was created using the optimum-static-quantization notebook.

It achieves the following results on the evaluation set:

Accuracy

  • Vanilla model: 92.5%
  • Quantized model: 92.24%

The quantized model achieves 99.72% accuracy of the fp32 model

Latency

Payload sequence length: 128
Instance type: AWS c6i.xlarge

latency vanilla transformers quantized optimum model improvement
p95 75.69ms 26.75ms 2.83x
avg 57.52ms 24.86ms 2.31x
How to use
from optimum.onnxruntime import ORTModelForSequenceClassification
from transformers import pipeline, AutoTokenizer

model = ORTModelForSequenceClassification.from_pretrained("philschmid/quantized-distilbert-banking77")
tokenizer = AutoTokenizer.from_pretrained("philschmid/quantized-distilbert-banking77")

remote_clx = pipeline("text-classification",model=model, tokenizer=tokenizer)

remote_clx("What is the exchange rate like on this app?")

Runs of philschmid quantized-distilbert-banking77 on huggingface.co

5
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
-4
30-day runs

More Information About quantized-distilbert-banking77 huggingface.co Model

quantized-distilbert-banking77 huggingface.co

quantized-distilbert-banking77 huggingface.co is an AI model on huggingface.co that provides quantized-distilbert-banking77's model effect (), which can be used instantly with this philschmid quantized-distilbert-banking77 model. huggingface.co supports a free trial of the quantized-distilbert-banking77 model, and also provides paid use of the quantized-distilbert-banking77. Support call quantized-distilbert-banking77 model through api, including Node.js, Python, http.

quantized-distilbert-banking77 huggingface.co Url

https://huggingface.co/philschmid/quantized-distilbert-banking77

philschmid quantized-distilbert-banking77 online free

quantized-distilbert-banking77 huggingface.co is an online trial and call api platform, which integrates quantized-distilbert-banking77's modeling effects, including api services, and provides a free online trial of quantized-distilbert-banking77, you can try quantized-distilbert-banking77 online for free by clicking the link below.

philschmid quantized-distilbert-banking77 online free url in huggingface.co:

https://huggingface.co/philschmid/quantized-distilbert-banking77

quantized-distilbert-banking77 install

quantized-distilbert-banking77 is an open source model from GitHub that offers a free installation service, and any user can find quantized-distilbert-banking77 on GitHub to install. At the same time, huggingface.co provides the effect of quantized-distilbert-banking77 install, users can directly use quantized-distilbert-banking77 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

quantized-distilbert-banking77 install url in huggingface.co:

https://huggingface.co/philschmid/quantized-distilbert-banking77

Url of quantized-distilbert-banking77

quantized-distilbert-banking77 huggingface.co Url

Provider of quantized-distilbert-banking77 huggingface.co

philschmid
ORGANIZATIONS

Other API from philschmid