Instructions to use tarekziade/wikipedia-topics-distilbert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tarekziade/wikipedia-topics-distilbert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="tarekziade/wikipedia-topics-distilbert")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("tarekziade/wikipedia-topics-distilbert") model = AutoModelForSequenceClassification.from_pretrained("tarekziade/wikipedia-topics-distilbert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download quantize_config.json from tarekziade/wikipedia-topics-distilbert: direct link, hf CLI and curl.
- Browser
- Download file 798 Bytes
-
https://huggingface.co/tarekziade/wikipedia-topics-distilbert/resolve/main/quantize_config.json
- Command line
-
hf download hf://tarekziade/wikipedia-topics-distilbert/quantize_config.json
-
curl -L -o quantize_config.json https://huggingface.co/tarekziade/wikipedia-topics-distilbert/resolve/main/quantize_config.json
798 Bytes
| { | |
| "per_channel": true, | |
| "reduce_range": true, | |
| "per_model_config": { | |
| "model": { | |
| "op_types": [ | |
| "MatMul", | |
| "Erf", | |
| "Pow", | |
| "Div", | |
| "Sub", | |
| "Concat", | |
| "Relu", | |
| "Constant", | |
| "Reshape", | |
| "Shape", | |
| "ReduceMean", | |
| "Transpose", | |
| "Add", | |
| "Expand", | |
| "Unsqueeze", | |
| "Where", | |
| "Softmax", | |
| "Gemm", | |
| "Sqrt", | |
| "Mul", | |
| "Gather", | |
| "Slice", | |
| "Cast", | |
| "Equal" | |
| ], | |
| "weight_type": "QInt8" | |
| } | |
| } | |
| } |