
atrifat/topic-classification
Classify short texts and tweets into topics. Accepts a text string and returns ranked topic labels with confidence score...
Found 13 models (showing 1-13)
Classify short texts and tweets into topics. Accepts a text string and returns ranked topic labels with confidence score...
Classify sentiment in text. Accepts a text input and returns a sentiment label with a confidence score, enabling quick a...
Detect whether text is AI-generated and return a likelihood score. Analyze input text and output the probability that it...
Score text prompts for NSFW/toxicity on a 0–10 safety scale. Accept a text prompt (e.g., for text-to-image systems) and...
Classify text for safety policy compliance. Takes a user prompt and/or an assistant response and returns a safe/unsafe l...
Generate and classify text from a prompt. Leverage a LLaMA 1 13B fine-tune oriented toward academic use cases such as te...
Classify sentiment in text as positive or negative. Accepts a text string and returns a binary label (POSITIVE or NEGATI...
Detect hate speech and toxic language in text. Accepts a text string and returns probability scores for toxicity, severe...
Classify text into user-provided categories and rank labels by confidence. Accepts a text sequence and a comma-separated...
Classify text into user-defined categories without training (zero-shot). Accepts an input text and a comma-separated lis...
Detect prompt injection and jailbreak attempts in text inputs. Accepts a text string and outputs multi-label classificat...
Moderate LLM conversations by classifying user prompts and assistant responses as SAFE or UNSAFE and listing violated po...
Classify sentiment of text. Takes a text string as input and returns an overall sentiment label (positive, negative, or...