Instructions to use windowsartes/fnet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use windowsartes/fnet with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="windowsartes/fnet")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("windowsartes/fnet") model = AutoModelForMaskedLM.from_pretrained("windowsartes/fnet", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from windowsartes/fnet: direct link, hf CLI and curl.
- Browser
- Download file 601 Bytes
-
https://huggingface.co/windowsartes/fnet/resolve/main/config.json
- Command line
-
hf download hf://windowsartes/fnet/config.json
-
curl -L -o config.json https://huggingface.co/windowsartes/fnet/resolve/main/config.json
601 Bytes
| { | |
| "_name_or_path": "/content/drive/MyDrive/model/fnet", | |
| "architectures": [ | |
| "FNetForMaskedLM" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu_new", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 384, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1536, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 26, | |
| "model_type": "fnet", | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 3, | |
| "torch_dtype": "float32", | |
| "tpu_short_seq_length": 512, | |
| "transformers_version": "4.40.1", | |
| "type_vocab_size": 4, | |
| "use_tpu_fourier_optimizations": false, | |
| "vocab_size": 911 | |
| } | |