Instructions to use keras/all_mpnet_base_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/all_mpnet_base_v2 with KerasHub:
import keras_hub # Create a TextEmbedder model task = keras_hub.models.TextEmbedder.from_preset("hf://keras/all_mpnet_base_v2")import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/all_mpnet_base_v2") - Keras
How to use keras/all_mpnet_base_v2 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/all_mpnet_base_v2") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from keras/all_mpnet_base_v2: direct link, hf CLI and curl.
- Browser
- Download file 766 Bytes
-
https://huggingface.co/keras/all_mpnet_base_v2/resolve/main/tokenizer.json
- Command line
-
hf download hf://keras/all_mpnet_base_v2/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/keras/all_mpnet_base_v2/resolve/main/tokenizer.json
766 Bytes
| { | |
| "module": "keras_hub.src.models.mpnet.mpnet_tokenizer", | |
| "class_name": "MPNetTokenizer", | |
| "config": { | |
| "name": "mp_net_tokenizer", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "int32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "config_file": "tokenizer.json", | |
| "vocabulary": null, | |
| "sequence_length": null, | |
| "lowercase": true, | |
| "strip_accents": true, | |
| "split": true, | |
| "suffix_indicator": "##", | |
| "oov_token": "[UNK]", | |
| "special_tokens": null, | |
| "special_tokens_in_strings": false | |
| }, | |
| "registered_name": "keras_hub>MPNetTokenizer" | |
| } |