Wrong Tiny Aya model

configs/models.yaml

@@ -7,8 +7,10 @@
 llm:
   default:                      # Core generation LLM — Tiny Aya (3B, multilingual)
     backend: tiny_aya
-    repo: CohereLabs/tiny-aya-global-GGUF
-    revision: a602ea7eeec3a4ad6f77a1b8cf6a53512824922b
+    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).