6 actions in 6 pieces of software · ranked by words, meaning and measured trust · 546 ms
modelrecord166,915 downloads/month
- fill-mask
Task: fill-mask
- fill-mask
modelrecord14,251 downloads/month
- feature-extraction
Task: feature-extraction
- feature-extraction
modelrecord5,818 downloads/month
- text-classification
Task: text-classification
- text-classification
modelrecord3,489 downloads/month
- sentence-similarity
Task: sentence-similarity
- sentence-similarity
modelrecord12,035 downloads/month
- question-answering
Task: question-answering
- question-answering
modelrecord51,511 downloads/month
- token-classification
Task: token-classification
- token-classification
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.