Instructions to use bndgyawali/switch-transformer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use bndgyawali/switch-transformer 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://bndgyawali/switch-transformer") - Notebooks
- Google Colab
- Kaggle
Download history.json from bndgyawali/switch-transformer: direct link, hf CLI and curl.
- Browser
- Download file 369 Bytes
-
https://huggingface.co/bndgyawali/switch-transformer/resolve/main/history.json
- Command line
-
hf download hf://bndgyawali/switch-transformer/history.json
-
curl -L -o history.json https://huggingface.co/bndgyawali/switch-transformer/resolve/main/history.json
369 Bytes
| { | |
| "accuracy": [ | |
| 0.8043599724769592, | |
| 0.9206399917602539, | |
| 0.9495599865913391 | |
| ], | |
| "loss": [ | |
| 1.4081658124923706, | |
| 1.2099701166152954, | |
| 1.1436405181884766 | |
| ], | |
| "val_accuracy": [ | |
| 0.8650000095367432, | |
| 0.8374000191688538, | |
| 0.856440007686615 | |
| ], | |
| "val_loss": [ | |
| 1.3130414485931396, | |
| 1.3868604898452759, | |
| 1.3563815355300903 | |
| ] | |
| } |