tiny-MiniCPM-OCR-Jev-for-testing-GGUF

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.

GGUF of ggml-org-dev/tiny-MiniCPM-OCR-Jev-for-testing, converted with convert_hf_to_gguf.py of llama.cpp (text model and mmproj in F16, then text model quantized to Q4_0 with llama-quantize, token embeddings and output included, and mmproj quantized to Q8_0). The vocab of the text GGUF is also cut with slice_vocab_gguf.py (special tokens, single characters, the BPE path of the decision label words and the first 2000 merges are kept, token ids are remapped): it tokenizes text differently from the original model, the HF repo keeps the full tokenizer. Used by the llama.cpp server tests of the openbmb-minicpm-ocr-jev decision type.

llama-server -hf ggml-org-dev/tiny-MiniCPM-OCR-Jev-for-testing-GGUF:Q4_0

License

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

Downloads last month
-
GGUF
Model size
356k params
Architecture
qwen35
Hardware compatibility
Log In to add your hardware

4-bit

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-GGUF