BERT Model Selector

The node allows to select a model from TensorFlow Hub or HuggingFace. The trusted models are added to the lists. For HuggingFace it is possible to paste the model name into the selector. In case you would like to test other models please refer to Advanced tab. The model can be cached on a disk.

Options

Settings

Allows to select the model from either TensorFlow Hub or HuggingFace. In case of HuggingFace it is also possible to only display models for zero-shot classification.

Select Model
Model selection from the chosen model provider (TensorFlow Hub or HuggingFace).
Cache directory
A path where the models will be stored for further usage.
Remote URL
An arbitrary link to a model. Use with caution since there is no guarantee that the model will be compatible with the node. Only active when Advanced tab checkbox is active. This feature is experimental, use with discretion.
Local folder
A path to the local model that was downloaded not by this node. Only active when Advanced tab checkbox is active. This feature is experimental, use with discretion.

Advanced

Enable Remote URL and Local path selection modes
Enable Remote URL and Local path selection modes - an experimental feature that makes it possible to pick any model from a remote or local source. There is no guarantee that the models will be compatible with the BERT extension.

Python

Python
Select one of the Python execution environment options:
  • use default Python environment for the Redfield BERT Nodes (can be configured on the preference page)
  • use Conda environment from a Conda flow variable (only selectable if such a flow variable is available)

Input Ports

This node has no input ports

Output Ports

Icon
The BERT model that was downloaded or read from cache.

Popular Predecessors

Popular Successors

Views

This node has no views

Workflows

Links

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.