ai-sage

/

Giga-Embeddings-instruct

like 53

Follow

ai-sage 145

(.venv) python3 ~/Sources/llama.cpp/convert_hf_to_gguf.py ./Giga-Embeddings-instruct --outtype bf16 
INFO:hf-to-gguf:Loading model: Giga-Embeddings-instruct
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
INFO:hf-to-gguf:gguf: loading model weight map from 'model.safetensors.index.json'
INFO:hf-to-gguf:gguf: loading model part 'model-00001-of-00003.safetensors'
Traceback (most recent call last):
  File "/Users/danilabagroff/Sources/llama.cpp/convert_hf_to_gguf.py", line 5758, in <module>
    main()
  File "/Users/danilabagroff/Sources/llama.cpp/convert_hf_to_gguf.py", line 5752, in main
    model_instance.write()
  File "/Users/danilabagroff/Sources/llama.cpp/convert_hf_to_gguf.py", line 400, in write
    self.prepare_tensors()
  File "/Users/danilabagroff/Sources/llama.cpp/convert_hf_to_gguf.py", line 1846, in prepare_tensors
    super().prepare_tensors()
  File "/Users/danilabagroff/Sources/llama.cpp/convert_hf_to_gguf.py", line 276, in prepare_tensors
    for new_name, data_torch in (self.modify_tensors(data_torch, name, bid)):
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/danilabagroff/Sources/llama.cpp/convert_hf_to_gguf.py", line 1814, in modify_tensors
    return [(self.map_tensor_name(name), data_torch)]
             ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/danilabagroff/Sources/llama.cpp/convert_hf_to_gguf.py", line 235, in map_tensor_name
    raise ValueError(f"Can not map tensor {name!r}")
ValueError: Can not map tensor 'latent_attention_model.cross_attend_blocks.0.fn.to_kv.weight'

Поддерживаю, без GGUF (или совместимости с llama.cpp) крайне сложно найти практическое применение данной модели в каких-либо приложениях