FINGU-AI

/

Chocolatine-Fusion-14B

like 3

Hi,
I'm having trouble converting this model using convert_hf_to_gguf file from llama.cpp, also the ollama create command doesn't work.
convert_hf_to_gguf error message:
ValueError: Can not map tensor 'model.layers.0.mlp.down_proj.weight.absmax'
ollama create error message:
Error: unknown data type: U8
Any ideas on how to fix these errors? Does it relate to model infrastructure? Thanks in advance!