| # Model registry — pin every revision by SHA or explicit tag. Never `latest`. | |
| # Read by src/backend/config.py:load_models_config(). | |
| # | |
| # After changing `embeddings`, rebuild the index: | |
| # uv run python scripts/build_index.py | |
| llm: | |
| default: # Core generation LLM — Tiny Aya (3B, multilingual) | |
| backend: tiny_aya | |
| repo: CohereLabs/tiny-aya-global # transformers (safetensors) repo — NOT the | |
| # -GGUF variant (GGUF has no HF tokenizer and | |
| # is only for the llama_cpp backend). | |
| revision: b2d281bab0beaecb3418d0c0dc53eaba90574011 | |
| # NOTE: CC-BY-NC + gated. Accept the license on the model page and set the | |
| # HF_TOKEN Space secret. Runs locally via transformers on the Space (ZeroGPU); | |
| # without a token, generation falls back / errors locally (retrieval still works). | |
| swap_in: # One-line swap via get_llm_client("swap_in") | |
| backend: minicpm | |
| repo: openbmb/MiniCPM3-4B # text LLM swap-in (adjust to a newer MiniCPM if desired) | |
| revision: | |
| # Future benchmark backend (GGUF over a llama.cpp OpenAI-compatible server). | |
| # Tiny Aya ships GGUF: CohereLabs/tiny-aya-global-GGUF | |
| # llama_cpp: | |
| # backend: llama_cpp | |
| # base_url: http://127.0.0.1:8080/v1 | |
| # repo: CohereLabs/tiny-aya-global-GGUF | |
| embeddings: # Query/passage embeddings for FAISS RAG | |
| repo: nvidia/llama-nemotron-embed-1b-v2 # Nemotron multilingual embed (1B, ungated) | |
| revision: 113abe4acafa848e77ead9c0623205e511932348 # TODO: pin a commit SHA before deploy | |
| loader: sentence-transformers # SentenceTransformer(..., trust_remote_code=True) | |
| query_prefix: "query: " # required by this model | |
| passage_prefix: "passage: " # required by this model | |
| normalize: true # L2-normalize so IndexFlatIP == cosine | |
| device: auto # auto → cuda on the ZeroGPU Space, cpu locally | |
| parsing: # document parsing (OCR / table extraction) | |
| repo: # TBD | |
| revision: # TBD | |