6 actions in 6 pieces of software · ranked by words, meaning and measured trust · 618 ms
modelrecord2,566 downloads/month
- fill-mask
Task: fill-mask
- fill-mask
modelrecord37,353 downloads/month
- token-classification
Task: token-classification
- token-classification
modelrecord8,773 downloads/month
- text-classification
Task: text-classification
- text-classification
modelrecord12,035 downloads/month
- question-answering
Task: question-answering
- question-answering
modelrecord503,998 downloads/month
- feature-extraction
Task: feature-extraction
- feature-extraction
modelrecord1,078 downloads/month
- sentence-similarity
Task: sentence-similarity
- sentence-similarity
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.