TensorFlow Hub Models
The following pretrained models are available to use for transfer learning with the Text Classification - TensorFlow algorithm.
The following models vary significantly in size, number of model parameters, training time, and inference latency for any given dataset. The best model for your use case depends on the complexity of your fine-tuning dataset and any requirements that you have on training time, inference latency, or model accuracy.
| Model Name | model_id |
Source |
|---|---|---|
|
BERT Base Uncased |
|
|
|
BERT Base Cased |
|
|
|
BERT Base Multilingual Cased |
|
|
|
Small BERT L-2_H-128_A-2 |
|
|
|
Small BERT L-2_H-256_A-4 |
|
|
|
Small BERT L-2_H-512_A-8 |
|
|
|
Small BERT L-2_H-768_A-12 |
|
|
|
Small BERT L-4_H-128_A-2 |
|
|
|
Small BERT L-4_H-256_A-4 |
|
|
|
Small BERT L-4_H-512_A-8 |
|
|
|
Small BERT L-4_H-768_A-12 |
|
|
|
Small BERT L-6_H-128_A-2 |
|
|
|
Small BERT L-6_H-256_A-4 |
|
|
|
Small BERT L-6_H-512_A-8 |
|
|
|
Small BERT L-6_H-768_A-12 |
|
|
|
Small BERT L-8_H-128_A-2 |
|
|
|
Small BERT L-8_H-256_A-4 |
|
|
|
Small BERT L-8_H-512_A-8 |
|
|
|
Small BERT L-8_H-768_A-12 |
|
|
|
Small BERT L-10_H-128_A-2 |
|
|
|
Small BERT L-10_H-256_A-4 |
|
|
|
Small BERT L-10_H-512_A-8 |
|
|
|
Small BERT L-10_H-768_A-12 |
|
|
|
Small BERT L-12_H-128_A-2 |
|
|
|
Small BERT L-12_H-256_A-4 |
|
|
|
Small BERT L-12_H-512_A-8 |
|
|
|
Small BERT L-12_H-768_A-12 |
|
|
|
BERT Large Uncased |
|
|
|
BERT Large Cased |
|
|
|
BERT Large Uncased Whole Word Masking |
|
|
|
BERT Large Cased Whole Word Masking |
|
|
|
ALBERT Base |
|
|
|
ELECTRA Small++ |
|
|
|
ELECTRA Base |
|
|
|
BERT Base Wikipedia and BooksCorpus |
|
|
|
BERT Base MEDLINE/PubMed |
|
|
|
Talking Heads Base |
|
|
|
Talking Heads Large |
|