10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 678 ms
modelrecord86,678 downloads/month
- feature-extraction
Task: feature-extraction
- feature-extraction
modelrecord13,512 downloads/month
- token-classification
Task: token-classification
- token-classification
modelrecord35,108 downloads/month
- automatic-speech-recognition
Task: automatic-speech-recognition
- automatic-speech-recognition
modelrecord2,439 downloads/month
- fill-mask
Task: fill-mask
- fill-mask
modelrecord105,834 downloads/month
- sentence-similarity
Task: sentence-similarity
- sentence-similarity
modelrecord3,000 downloads/month
- text-classification
Task: text-classification
- text-classification
modelrecord10,202 downloads/month
- zero-shot-classification
Task: zero-shot-classification
- zero-shot-classification
modelrecord
- adirik/multilingual-e5-large
Multilingual E5-large language embedding model
- adirik/multilingual-e5-large
modelrecord20 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord20,427 downloads/month
- translation
Task: translation
- translation
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.