Upload folder using huggingface_hub

README.md

@@ -15,64 +15,27 @@ language:
 - zh
 - ar
 tags:
-- mlx
 - vision
 - multimodal
 - conversational
 - multilingual
 - native-resolution
+- mlx
 base_model: CohereLabs/North-Micro-Vision-Instruct
-base_model_relation: quantized
 ---
 
-# North Micro Vision Instruct — NVFP4 (MLX)
-
-This repository contains an **MLX conversion** of [CohereLabs/North-Micro-Vision-Instruct](https://huggingface.co/CohereLabs/North-Micro-Vision-Instruct), prepared for inference with [MLX-VLM](https://github.com/Blaizzy/mlx-vlm).
-
-North Micro Vision Instruct is a compact 2.4B-parameter vision-language model from Cohere. It supports native-resolution and multi-image inputs, multilingual conversations, visual question answering, captioning, grounding, OCR, and chart/document understanding.
-
-## Conversion details
-
-- **Quantization:** NVFP4
-- **Bits:** 4
-- **Group size:** 16
-- **Vision tower:** Preserved in the source precision
-
-The model weights were converted from the official checkpoint. Refer to the [original model card](https://huggingface.co/CohereLabs/North-Micro-Vision-Instruct) for architecture details, evaluation results, intended uses, and limitations.
-
-## Installation
-
-Cohere Compass support is currently available on the MLX-VLM port branch. Until it is included in a released package, install it with:
+# mlx-community/North-Micro-Vision-Instruct-nvfp4
 
-```bash
-pip install -U "git+https://github.com/Blaizzy/mlx-vlm.git@pc/mlx-vlm-port"
-```
+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.
 
-After Compass support is released, the standard package can be used:
+## Use with mlx
 
 ```bash
 pip install -U mlx-vlm
 ```
 
-## Usage
-
 ```bash
-mlx_vlm.generate \
-  --model mlx-community/North-Micro-Vision-Instruct-nvfp4 \
-  --image <path-or-URL-to-image> \
-  --prompt "What do you see?" \
-  --max-tokens 128 \
-  --temperature 0
+python -m mlx_vlm.generate --model mlx-community/North-Micro-Vision-Instruct-nvfp4 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
 ```
-
-On Apple silicon, this format runs directly. On MLX CUDA, pass `--quantize-activations` (or `-qa`) for this quantization mode.
-
-The original model was trained with multimodal contexts up to 8K tokens. Although its language backbone supports a longer context, longer multimodal prompts were not validated by the model authors.
-
-## Other MLX variants
-
-BF16 and quantized conversions are available in the [North-Vision collection](https://huggingface.co/collections/mlx-community/north-vision-6a7c9be6ccc1cd992a83aecb).
-
-## License
-
-This conversion is released under the source model's [Apache 2.0 license](https://www.apache.org/licenses/LICENSE-2.0). Use is also subject to the limitations and responsible-use guidance in the [original model card](https://huggingface.co/CohereLabs/North-Micro-Vision-Instruct).

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3637dcf3bcf90aefbddad6c8b8f6b66cd6c52ec816b7388ab40b6977ef4fa94
+oid sha256:f15b00db530161dc15f7462bfcfde450030406fb0756bcc2571544f0cda36a0b
 size 2172188587