Instructions to use Mozilla/tinybert-uncased-autofill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mozilla/tinybert-uncased-autofill with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Mozilla/tinybert-uncased-autofill")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Mozilla/tinybert-uncased-autofill") model = AutoModelForSequenceClassification.from_pretrained("Mozilla/tinybert-uncased-autofill", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "modes": [ | |
| "fp16", | |
| "q8", | |
| "int8", | |
| "uint8", | |
| "q4", | |
| "q4f16", | |
| "bnb4" | |
| ], | |
| "per_channel": true, | |
| "reduce_range": true, | |
| "block_size": null, | |
| "is_symmetric": true, | |
| "accuracy_level": null, | |
| "quant_type": 1 | |
| } |