Text Classification
Transformers
PyTorch
Russian
bert
russian
pretraining
conversational
text-embeddings-inference
Instructions to use t-bank-ai/response-toxicity-classifier-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use t-bank-ai/response-toxicity-classifier-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="t-bank-ai/response-toxicity-classifier-base") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("t-bank-ai/response-toxicity-classifier-base") model = AutoModelForSequenceClassification.from_pretrained("t-bank-ai/response-toxicity-classifier-base") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 30513ad81f845180b90ce8d5be4b2ce43623c7feec7c41e53c41a7a2d8562fe4
- Size of remote file:
- 654 MB
- SHA256:
- 13065d0cededdc25f4253ef9a14856dd8c3a8958dec4fc13ca01ba9e3c0a52c6
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.