Instructions to use nanom/vizwiz-bert-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nanom/vizwiz-bert-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="nanom/vizwiz-bert-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("nanom/vizwiz-bert-base") model = AutoModelForMaskedLM.from_pretrained("nanom/vizwiz-bert-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download hyperparams.json from nanom/vizwiz-bert-base: direct link, hf CLI and curl.
- Browser
- Download file 147 Bytes
-
https://huggingface.co/nanom/vizwiz-bert-base/resolve/main/hyperparams.json
- Command line
-
hf download hf://nanom/vizwiz-bert-base/hyperparams.json
-
curl -L -o hyperparams.json https://huggingface.co/nanom/vizwiz-bert-base/resolve/main/hyperparams.json
147 Bytes
| {"RANDOM_SEED": 16, "MAX_TOKEN_LEN": 78, "TRAIN_BATCH_SIZE": 32, "VAL_BATCH_SIZE": 16, "NUM_EPOCHS": 5, "LEARNING_RATE": 5e-06, "TRAIN_SPLIT": 0.8} |