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
-
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