Text Classification
Transformers
Safetensors
English
roberta
guardrails
safety
education
code
cs-education
llm-safety
academic-integrity
Eval Results (legacy)
text-embeddings-inference
Instructions to use md-nishat-008/PromptShield with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use md-nishat-008/PromptShield with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="md-nishat-008/PromptShield")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("md-nishat-008/PromptShield") model = AutoModelForSequenceClassification.from_pretrained("md-nishat-008/PromptShield") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 70be38c69f90fef68c94d01971d7b0192280c2aa34e36e2ed73c5a0bbc89c35f
- Size of remote file:
- 5.24 kB
- SHA256:
- 30f035b6b6b87153eef366fffafc958d3975f7b7b57f0bf48544defc396164ec
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.