there‘s a problem when I make it to .gguf
My English is not very good, please forgive me.
I want make it to gguf with llama.cpp,but wen I run 'python llama.cpp\convert_hf_to_gguf.py .\Occult-Roleplay-Mixtral-4x7B --outtype f16',there's a wrong.
D:\model>python llama.cpp\convert_hf_to_gguf.py .\Occult-Roleplay-Mixtral-4x7B --outtype f16
INFO:hf-to-gguf:Loading model: Occult-Roleplay-Mixtral-4x7B
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'
Traceback (most recent call last):
File "D:\model\llama.cpp\convert_hf_to_gguf.py", line 3673, in
main()
File "D:\model\llama.cpp\convert_hf_to_gguf.py", line 3667, in main
model_instance.write()
File "D:\model\llama.cpp\convert_hf_to_gguf.py", line 396, in write
self.prepare_tensors()
File "D:\model\llama.cpp\convert_hf_to_gguf.py", line 1558, in prepare_tensors
super().prepare_tensors()
File "D:\model\llama.cpp\convert_hf_to_gguf.py", line 263, in prepare_tensors
for name, data_torch in self.get_tensors():
File "D:\model\llama.cpp\convert_hf_to_gguf.py", line 137, in get_tensors
with open(self.dir_model / index_name, "r", encoding="utf-8") as f:
FileNotFoundError: [Errno 2] No such file or directory: 'Occult-Roleplay-Mixtral-4x7B\model.safetensors.index.json'