A tool-calling layer, not a language model — your schemas in, validated calls out, at 48M parameters. Malformed JSON, invented parameter names, and undeclared tools are structurally unreachable on any catalog. Adapt it to your own catalog; 11 negative results included.
c inference-engine edge-ai int8-quantization constrained-decoding llm function-calling small-language-model tool-calling grammar-based-decoding
-
Updated
Aug 25, 2026 - Python