Misc. bug: convert_hf_to_gguf.py: ValueError: Can not map tensor 'model.layers.0.mlp.down_proj.weight_scale'

[evaninf]

Name and Version

version: 4410 (4b0c638b) built with cc (GCC) 14.2.1 20240912 (Red Hat 14.2.1-3) for x86_64-redhat-linux

Operating systems

Linux

Which llama.cpp modules do you know to be affected?

Python/Bash scripts

Command line

python ./convert_hf_to_gguf.py ~/downloads/Falcon3-10B-Instruct-1.58bit/

Problem description & steps to reproduce

Trying to convert tiiuae/Falcon3-10B-Instruct-1.58bit to GGUF results in the error.

First Bad Commit

No response

Relevant log output

INFO:hf-to-gguf:Loading model: Falcon3-10B-Instruct-1.58bit
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 part 'model.safetensors'
INFO:hf-to-gguf:output.weight,               torch.bfloat16 --> F16, shape = {3072, 131072}
INFO:hf-to-gguf:token_embd.weight,           torch.bfloat16 --> F16, shape = {3072, 131072}
INFO:hf-to-gguf:blk.0.attn_norm.weight,      torch.bfloat16 --> F32, shape = {3072}
INFO:hf-to-gguf:blk.0.ffn_down.weight,       torch.uint8 --> F16, shape = {23040, 768}
Traceback (most recent call last):
  File "/mnt/src/llama.cpp/./convert_hf_to_gguf.py", line 4929, in <module>
    main()
  File "/mnt/src/llama.cpp/./convert_hf_to_gguf.py", line 4923, in main
    model_instance.write()
  File "/mnt/src/llama.cpp/./convert_hf_to_gguf.py", line 438, in write
    self.prepare_tensors()
  File "/mnt/src/llama.cpp/./convert_hf_to_gguf.py", line 1692, in prepare_tensors
    super().prepare_tensors()
  File "/mnt/src/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 "/mnt/src/llama.cpp/./convert_hf_to_gguf.py", line 1660, in modify_tensors
    return [(self.map_tensor_name(name), data_torch)]
             ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/mnt/src/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.weight_scale'