Instructions to use paulbauriegel/digital-fridge-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use paulbauriegel/digital-fridge-models with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Digital Fridge models
Models downloaded by the Digital Fridge Android app
(paulbauriegel/digital-fride-app).
catalog.json on main lists every file the app can download, each pinned to a commit with its
sha256. The GLM-OCR GGUF pair and Granite 4.0 350M are downloaded from their upstream repos; only the
LiteRT conversion below is hosted here.
glm-ocr-litert/: GLM-OCR for LiteRT (experimental)
A conversion of zai-org/GLM-OCR at revision
ca5d8b3e287e52589e37c28385d9655ee4372f9d for LiteRT 2.1.5 on Android: a fixed 644 ร 952 vision
encoder (glm_ocr_vision_68x46_fp32.tflite) and a cached multimodal decoder
(glm_ocr_multimodal_decoder_combined_fp16.tflite, float16 weights). Converted with litert-torch
0.9.1 and torch 2.7.1+cpu by convert-glm-ocr-litert.sh (included);
glm_ocr_litert_conversion_manifest.json records shapes, hashes and validation results.
Licence: MIT, as declared by the original GLM-OCR model card (see LICENSE).
- Downloads last month
- 16
Model tree for paulbauriegel/digital-fridge-models
Base model
zai-org/GLM-OCR