Convert ERROR : lama.cpp/convert_hf_to_gguf.py
(ollama_webui) [radmin@gpu01 finnish]$ python ~/gitlab/llama.cpp/convert_hf_to_gguf.py . --outfile QVQ-72B-Preview-abliterated-GPTQ-Int8.gguf
INFO:hf-to-gguf:Loading model:
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-00016.safetensors'
INFO:hf-to-gguf:token_embd.weight, torch.float16 --> F16, shape = {8192, 152064}
INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.float16 --> F32, shape = {8192}
Traceback (most recent call last):
File "/data01/radmin/gitlab/llama.cpp/convert_hf_to_gguf.py", line 5140, in
main()
File "/data01/radmin/gitlab/llama.cpp/convert_hf_to_gguf.py", line 5134, in main
model_instance.write()
File "/data01/radmin/gitlab/llama.cpp/convert_hf_to_gguf.py", line 439, in write
self.prepare_tensors()
File "/data01/radmin/gitlab/llama.cpp/convert_hf_to_gguf.py", line 298, in prepare_tensors
for new_name, data_torch in (self.modify_tensors(data_torch, name, bid)):
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data01/radmin/gitlab/llama.cpp/convert_hf_to_gguf.py", line 266, in modify_tensors
return [(self.map_tensor_name(name), data_torch)]
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/data01/radmin/gitlab/llama.cpp/convert_hf_to_gguf.py", line 214, in map_tensor_name
raise ValueError(f"Can not map tensor {name!r}")
ValueError: Can not map tensor 'model.layers.0.mlp.down_proj.g_idx'