Restore BF16 model card after CLI reconversion

README.md

@@ -4,38 +4,70 @@ license: apache-2.0
 pipeline_tag: image-text-to-text
 language:
 - en
-- de
-- fr
-- es
-- it
-- pt
-- hi
-- ja
-- ko
-- zh
-- ar
 tags:
-- vision
-- multimodal
-- conversational
-- multilingual
-- native-resolution
 - mlx
+- mlx-vlm
+- vision-language
+- multimodal
+- cohere
+- north
 base_model: CohereLabs/North-Micro-Vision-Instruct
 ---
 
-# mlx-community/North-Micro-Vision-Instruct-bf16
+# North Micro Vision Instruct — BF16 (MLX)
+
+This repository contains an Apple MLX conversion of
+[CohereLabs/North-Micro-Vision-Instruct](https://huggingface.co/CohereLabs/North-Micro-Vision-Instruct). BF16 MLX weights (no weight quantization).
+
+It belongs to the
+[North Vision MLX collection](https://huggingface.co/collections/mlx-community/north-vision-6a7c9be6ccc1cd992a83aecb), which includes BF16, affine
+4/5/6/8-bit, MXFP4, MXFP8, and NVFP4 variants.
+
+## Conversion details
+
+- Source: [CohereLabs/North-Micro-Vision-Instruct](https://huggingface.co/CohereLabs/North-Micro-Vision-Instruct)
+- Format: MLX / MLX-VLM
+- Precision: bfloat16 (unquantized)
+- MLX-VLM source revision: main at 7ee8eba3
+
+The repository was regenerated and uploaded directly with the MLX-VLM
+conversion CLI:
+
+~~~bash
+python -m mlx_vlm convert \
+  --hf-path CohereLabs/North-Micro-Vision-Instruct \
+  --mlx-path North-Micro-Vision-Instruct-bf16 \
+  --dtype bfloat16 \
+  --upload-repo mlx-community/North-Micro-Vision-Instruct-bf16
+~~~
+
+## Usage
+
+Cohere Compass support is available on the current MLX-VLM main branch.
+Install it directly from GitHub:
+
+~~~bash
+pip install -U "mlx-vlm @ git+https://github.com/Blaizzy/mlx-vlm.git"
+~~~
+
+Run vision-language inference:
 
-This model was converted to MLX format from [`CohereLabs/North-Micro-Vision-Instruct`](https://huggingface.co/CohereLabs/North-Micro-Vision-Instruct)
-using mlx-vlm version **0.6.13**.
-Refer to the [original model card](https://huggingface.co/CohereLabs/North-Micro-Vision-Instruct) for more details on the model.
+~~~bash
+mlx_vlm.generate \
+  --model mlx-community/North-Micro-Vision-Instruct-bf16 \
+  --image /path/to/image.jpg \
+  --prompt "Describe this image." \
+  --max-tokens 512 \
+  --temperature 0.0
+~~~
 
-## Use with mlx
+You can also pass an image URL to --image.
 
-```bash
-pip install -U mlx-vlm
-```
+## Notes
 
-```bash
-python -m mlx_vlm.generate --model mlx-community/North-Micro-Vision-Instruct-bf16 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
-```
+- MLX is optimized for Apple silicon.
+- This repository changes the storage precision/quantization, not the source
+  model architecture or intended behavior.
+- Refer to the
+  [original model card](https://huggingface.co/CohereLabs/North-Micro-Vision-Instruct) for capabilities,
+  limitations, licensing context, and responsible-use guidance.