Open
Description
Name and Version
This tutorial doesn't work
This line need to be fixed
python ./examples/convert_legacy_llama.py ../llava-v1.6-vicuna-7b/ --skip-unknown
Operating systems
Linux
GGML backends
CUDA
Hardware
A100
Models
No response
Problem description & steps to reproduce
https://github.com/ggml-org/llama.cpp/blob/master/docs/multimodal/llava.md#llava-16-gguf-conversion
This is not working
First Bad Commit
No response
Relevant log output
Most errors are related to mismatched key errors such as image_newline