10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 602 ms
modelrecord563,188 downloads/month
- sentence-similarity
Task: sentence-similarity
- sentence-similarity
modelrecord
- zsxkib/embedding-gemma-300m
Turn any text into 768-dimensional vectors for search, classification, and AI apps 🧠✨
- zsxkib/embedding-gemma-300m
modelrecord197,761 downloads/month
- feature-extraction
Task: feature-extraction
- feature-extraction
modelrecord13,786 downloads/month
- any-to-any
Task: any-to-any
- any-to-any
modelrecord
- yanexr/embedding-gemma-2
Google DeepMind’s 740M multimodal embedding model. Embed text, images, video and audio into one shared 768-dimensional space (or 512, 256, 128), with an 8K token input window.
- yanexr/embedding-gemma-2
modelrecord192,708 downloads/month
- automatic-speech-recognition
Task: automatic-speech-recognition
- automatic-speech-recognition
modelrecord27,670 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord134,811 downloads/month
- fill-mask
Task: fill-mask
- fill-mask
- 9EmbeddingGemma 2 Semantic Playgrounddemo or tutorialno passport yet
MCP serverrecord
- embeddinggemma_2_demo_compare
Compare all pairs of sentences using normalized sentence-similarity embeddings.
- embeddinggemma_2_demo_compare
- sherpa-onnx-tts
Local text-to-speech via sherpa-onnx (offline, no cloud)
- sherpa-onnx-tts
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.