Downloads · 30 days
16
7% of all-time downloads
RolmOCR-mlx-fp16
dicksonhk/RolmOCR-mlx-fp16
RolmOCR-mlx-fp16 is a image-text-to-text model from dicksonhk. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
The Model dicksonhk/RolmOCR-mlx-fp16 was converted to $MLX format from reducto/RolmOCR using $mlx-vlm version 0.1.15.
All-time downloads
243
Public
Parameters
8.3B
16.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.6 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen2_5_vl
- Access
- Public
- Created
- Jun 18, 2025
- Updated
- Jun 18, 2025
- SHA
- 50381af7
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
dicksonhk/RolmOCR-mlx-fp16
The Model [dicksonhk/RolmOCR-mlx-fp16](https://huggingface.co/dicksonhk/RolmOCR-mlx-fp16) was converted to $MLX format from [reducto/RolmOCR](https://huggingface.co/reducto/RolmOCR) using $mlx-vlm version **0.1.15**.
pip install -U mlx-vlm
python -m mlx_vlm.generate --model dicksonhk/RolmOCR-mlx-fp16 --max-tokens 100 --temp 0.0 --prompt "Describe this image." --image <path_to_image>
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen2_5_vl
- License
- apache-2.0
- Created
- Jun 18, 2025
- Updated
- Jun 18, 2025