maidalun1020

/

bce-embedding-base_v1

like 242

python llm/llama.cpp/convert-hf-to-gguf.py bce-embedding-base_v1 --outtype f16 --outfile bce-embedding-base_v1_converted/bce-embedding-base_v1.bin
INFO:hf-to-gguf:Loading model: bce-embedding-base_v1
Traceback (most recent call last):
  File "/llm/llama.cpp/convert-hf-to-gguf.py", line 2562, in <module>
    main()
  File "/llm/llama.cpp/convert-hf-to-gguf.py", line 2540, in main
    model_class = Model.from_model_architecture(hparams["architectures"][0])
  File "/llm/llama.cpp/convert-hf-to-gguf.py", line 382, in from_model_architecture
    raise NotImplementedError(f'Architecture {arch!r} not supported!') from None
NotImplementedError: Architecture 'XLMRobertaModel' not supported!