Failed to load CLIP

#1
by engrtipusultan - opened

I am using lama-b6700-bin-ubuntu-vulkan-x64.
settings

  • name: granite-docling
    model_path: /home/tipu/AI/models/ggml-org/Granite_docling/granite-docling-258M-f16.gguf
    model_params: |
    --port 8888
    --api-key 12345
    --mmproj /home/tipu/AI/models/ggml-org/Granite_docling/granite-docling-258M-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 granite-docling
    --mlock
    --seed -1
    --no-mmap

I cannot load this model.

mtmd_init_from_file: error: Failed to load CLIP model from /home/tipu/AI/models/ggml-org/Granite_docling/granite-docling-258M-f16.gguf

srv load_model: failed to load multimodal model, '/home/tipu/AI/models/ggml-org/Granite_docling/granite-docling-258M-f16.gguf'
srv operator(): operator(): cleaning up before exit...
main: exiting due to model loading error

ggml.ai org

You are loading the text model as both regular and mmproj model, use the mmproj-granite-docling-258M-f16.gguffile for --mmproj instead.

Ohh crap. Thanks CISC I was trying bunch of things at that time. I totally missed I was calling the wrong file. Thank once again. I will recheck with correct reference.

engrtipusultan changed discussion status to closed

Sign up or log in to comment