Instructions to use inep/twitter-roberta-base-sentiment-js with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use inep/twitter-roberta-base-sentiment-js with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="inep/twitter-roberta-base-sentiment-js")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("inep/twitter-roberta-base-sentiment-js") model = AutoModelForSequenceClassification.from_pretrained("inep/twitter-roberta-base-sentiment-js", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download quantize_config.json from inep/twitter-roberta-base-sentiment-js: direct link, hf CLI and curl.
- Browser
- Download file 882 Bytes
-
https://huggingface.co/inep/twitter-roberta-base-sentiment-js/resolve/main/quantize_config.json
- Command line
-
hf download hf://inep/twitter-roberta-base-sentiment-js/quantize_config.json
-
curl -L -o quantize_config.json https://huggingface.co/inep/twitter-roberta-base-sentiment-js/resolve/main/quantize_config.json
882 Bytes
| { | |
| "per_channel": true, | |
| "reduce_range": true, | |
| "per_model_config": { | |
| "model": { | |
| "op_types": [ | |
| "Shape", | |
| "Slice", | |
| "Gather", | |
| "ReduceMean", | |
| "Erf", | |
| "Transpose", | |
| "Softmax", | |
| "Expand", | |
| "ConstantOfShape", | |
| "Add", | |
| "Concat", | |
| "MatMul", | |
| "Not", | |
| "Constant", | |
| "Unsqueeze", | |
| "Gemm", | |
| "Equal", | |
| "Pow", | |
| "Mul", | |
| "Div", | |
| "CumSum", | |
| "Reshape", | |
| "Cast", | |
| "Tanh", | |
| "Where", | |
| "Sub", | |
| "Sqrt" | |
| ], | |
| "weight_type": "QInt8" | |
| } | |
| } | |
| } |