Add license+base_model metadata; link to upstream

README.md

@@ -1,4 +1,6 @@
 ---
+license: apache-2.0
+base_model: mistralai/Voxtral-Mini-3B-2507
 tags:
   - voxtral
   - quantized
@@ -8,7 +10,7 @@ library_name: mlx
 
 # Voxtral 3B — Quantized (MLX)
 
-Public quantized weights of the Voxtral 3B model for Apple MLX. This repo contains MLX-ready variants only.
+Public quantized weights of the upstream model [`mistralai/Voxtral-Mini-3B-2507`](https://huggingface.co/mistralai/Voxtral-Mini-3B-2507). This repo contains MLX-ready variants only.
 
 ## Variants
 - MLX Q4: `mlx-q4/`
@@ -36,7 +38,7 @@ print(generate(model, tokenizer, prompt, max_tokens=64))
 - Embeddings are NOT quantized to preserve shape compatibility. As a result, any "bits per weight" metric may exceed the nominal target. This is informational, not an error.
 
 ## License
-- See `LICENSE.txt`. Also ensure you comply with the original Voxtral model license.
+- License: Apache-2.0 (see `LICENSE.txt`). Attribution: upstream model [`mistralai/Voxtral-Mini-3B-2507`](https://huggingface.co/mistralai/Voxtral-Mini-3B-2507).
 
 ## Issues
 If you notice any mismatch (missing files, wrong checksum), please open an issue.