mlx-community/dots.mocr-8bit
This model was converted to MLX format from rednote-hilab/dots.mocr
using mlx-vlm version 0.4.1.
Refer to the original model card for more details on the model.
Use with mlx
pip install -U mlx-vlm
python -m mlx_vlm.generate --model mlx-community/dots.mocr-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
- Downloads last month
- 17
Model size
2B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
8-bit
Model tree for mlx-community/dots.mocr-8bit
Base model
rednote-hilab/dots.mocrEvaluation results
- Overall on allenai/olmOCR-bench View evaluation results source leaderboard
83.9 - Arxiv Math on allenai/olmOCR-bench View evaluation results source leaderboard 85.9
- Old Scans Math on allenai/olmOCR-bench View evaluation results source leaderboard 85.5
- Table Tests on allenai/olmOCR-bench View evaluation results source leaderboard 90.7
- Old Scans on allenai/olmOCR-bench View evaluation results source leaderboard 48.2
- Multi Column on allenai/olmOCR-bench View evaluation results source leaderboard 85.3
- Long Tiny Text on allenai/olmOCR-bench View evaluation results source leaderboard 81.6
- Headers Footers on allenai/olmOCR-bench View evaluation results source leaderboard 94
- Baseline on allenai/olmOCR-bench View evaluation results source leaderboard 99.7