tiny-MiniCPM-OCR-Jev-for-testing

This is a modified, damaged copy of openbmb/MiniCPM-OCR-Jev, made only to test software. Its output is gibberish. Do not use it for anything else.

It keeps the architecture, tokenizer, chat template, image processor config and 2-class score head of MiniCPM-OCR-Jev, so it runs the same code paths as the real model in llama.cpp (openbmb-minicpm-ocr-jev decision type: Qwen3.5 trunk with linear and full attention, class scores read at the last token, 2 images per request), but it is small enough for CI.

GGUF version: ggml-org-dev/tiny-MiniCPM-OCR-Jev-for-testing-GGUF

Changes from the original model

Sliced from the safetensors with slice_minicpm_ocr_jev.py, which follows the slice-model skill of llama.cpp:

  • Text model: 4 of 24 layers (0-3: 3 linear attention + 1 full attention), hidden size 2048 -> 32, FFN 6144 -> 128, heads 8 -> 2, KV heads 2 -> 1, linear attention key and value heads 16 -> 2 (head dims kept)
  • Score head (score.weight, [inconsistent, consistent]): hidden size 2048 -> 32
  • Vision encoder: 2 of 24 blocks (0, 1), hidden size 1024 -> 128, heads 16 -> 2, FFN 4096 -> 256, output size 2048 -> 32
  • config.json declares MiniCPMOCRForSequenceClassification instead of Qwen3_5ForConditionalGeneration, so that convert_hf_to_gguf.py converts it as the sequence classifier
  • The original repo has no LICENSE file, the Apache License 2.0 text is added

License

Derived from MiniCPM-OCR-Jev by OpenBMB, under the Apache License 2.0.

Downloads last month
14
Safetensors
Model size
9.23M params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for ggml-org-dev/tiny-MiniCPM-OCR-Jev-for-testing

Finetuned
Qwen/Qwen3.5-2B
Finetuned
(4)
this model
Quantizations
1 model