Instructions to use keras/t5_base_multi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/t5_base_multi with KerasHub:
import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/t5_base_multi") - Keras
How to use keras/t5_base_multi with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://keras/t5_base_multi") - Notebooks
- Google Colab
- Kaggle
Download config.json from keras/t5_base_multi: direct link, hf CLI and curl.
- Browser
- Download file 560 Bytes
-
https://huggingface.co/keras/t5_base_multi/resolve/main/config.json
- Command line
-
hf download hf://keras/t5_base_multi/config.json
-
curl -L -o config.json https://huggingface.co/keras/t5_base_multi/resolve/main/config.json
560 Bytes
| { | |
| "module": "keras_hub.src.models.t5.t5_backbone", | |
| "class_name": "T5Backbone", | |
| "config": { | |
| "name": "t5_backbone", | |
| "trainable": true, | |
| "vocabulary_size": 32128, | |
| "hidden_dim": 768, | |
| "intermediate_dim": 3072, | |
| "num_layers": 12, | |
| "num_heads": 12, | |
| "activation": "relu", | |
| "key_value_dim": null, | |
| "dropout": 0.1, | |
| "use_gated_activation": false, | |
| "layer_norm_epsilon": 1e-06, | |
| "tie_embedding_weights": true | |
| }, | |
| "registered_name": "keras_hub>T5Backbone" | |
| } |