opendatalab

/

MinerU2.5-2509-1.2B

like 263

Follow

OpenDataLab 353

I am using MinerU2.5-2509-1.2B.f16.gguf and MinerU2.5-2509-1.2B.mmproj-f16.gguf
https://huggingface.co/mradermacher/MinerU2.5-2509-1.2B-GGUF

I am unable to do simple text OCR. My settings are as below. Any idea how to properly run in llama.cpp ?

• name: MinerU
  model_path: /home/tipu/AI/models/other/MinerU/MinerU2.5-2509-1.2B.f16.gguf
  model_params: |
  --port 8888
  --api-key 12345
  --mmproj /home/tipu/AI/models/other/MinerU/MinerU2.5-2509-1.2B.mmproj-f16.gguf
  --n-predict -1
  --n-gpu-layers 99
  --jinja
  --repeat-penalty 1.0
  --temp 0.0
  --min-p 0
  --threads 4
  --no-webui
  --alias MinerU
  --ctx-size 10240
  --ubatch-size 512
  --batch-size 4096
  --mlock
  --seed -1
  --swa-full
  --no-escape
  --no-mmap