Model Overview

It is a TT-compressed model of bert-base-uncased stsb model. Model was trained on STSB corpus with 0.87 combined score, and TTM-compressed with additional finetuning up to 58% (64 mln params) of original size with 0.843 score.

How to use

  tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
  model = AutoModelForSequenceClassification.from_pretrained("s-nlp/bert-base-uncased-stsb-TTM", trust_remote_code=True)

license: other

Downloads last month
10
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The HF Inference API does not support model that require custom code execution.