README.md

metadata

license: apache-2.0
datasets:
  - allenai/olmOCR-mix-0225
  - prithivMLmods/Opendoc1-Analysis-Recognition
  - prithivMLmods/Opendoc2-Analysis-Recognition
  - prithivMLmods/Openpdf-Analysis-Recognition
pipeline_tag: image-text-to-text
tags:
  - OCR
  - Pdf
  - Doc
  - Image
  - text-generation-inference
  - KIE-Key Information Extraction
  - mlx
  - mlx-my-repo
language:
  - en
  - zh
base_model: prithivMLmods/docscopeOCR-7B-050425-exp
library_name: transformers

dicksonhk/docscopeOCR-7B-050425-exp-mlx-fp16

The Model dicksonhk/docscopeOCR-7B-050425-exp-mlx-fp16 was converted to MLX format from prithivMLmods/docscopeOCR-7B-050425-exp using mlx-vlm version 0.1.15.

pip install -U mlx-vlm

python -m mlx_vlm.generate --model dicksonhk/docscopeOCR-7B-050425-exp-mlx-fp16 --max-tokens 100 --temp 0.0 --prompt "Describe this image." --image <path_to_image>