GGUF
I'm trying to create gguf quants using https://huggingface.co./spaces/ggml-org/gguf-my-repo
This is the error I get:
Error converting to fp16: INFO:hf-to-gguf:Loading model: openmusic
Traceback (most recent call last):
File "/home/user/app/./llama.cpp/convert_hf_to_gguf.py", line 4929, in
main()
File "/home/user/app/./llama.cpp/convert_hf_to_gguf.py", line 4897, in main
hparams = Model.load_hparams(dir_model)
File "/home/user/app/./llama.cpp/convert_hf_to_gguf.py", line 467, in load_hparams
with open(dir_model / "config.json", "r", encoding="utf-8") as f:
FileNotFoundError: [Errno 2] No such file or directory: 'downloads/tmpbtkqpllj/openmusic/config.json'
I didn't find any config.json neither
My main purpose is actually to be able to run the model on android device.
I'd appreciate it if you could help with that
Hello
@AlirezaHoseini
, can you try with from the error log i see it's searching config.json files which is used for transformers models, for diffusers models (this one) , we're using model_index.json (instead of config.json)