When trying to convert my quantized LoRA model from HF to GGUF using convert-hf-to-gguf.py I get the below error:
ValueError: Can not map tensor 'model.layers.0.mlp.down_proj.qweight'
Expected behavior: Conversion should have succeeded.
Name and Version
convert-hf-to-gguf.py, python 3.11.6
What operating system are you seeing the problem on?
No response
Relevant log output
python convert-hf-to-gguf.py <HF model directory>
INFO:hf-to-gguf:Loading model: <redacted>
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Set model parameters
INFO:hf-to-gguf:gguf: context length = 8192
INFO:hf-to-gguf:gguf: embedding length = 4096
INFO:hf-to-gguf:gguf: feed forward length = 14336
INFO:hf-to-gguf:gguf: head count = 32
INFO:hf-to-gguf:gguf: key-value head count = 8
INFO:hf-to-gguf:gguf: rope theta = 500000.0
INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-05
INFO:hf-to-gguf:gguf: file type = 1
INFO:hf-to-gguf:Set model tokenizer
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
INFO:gguf.vocab:Adding 280147 merge(s).
INFO:gguf.vocab:Setting special token type bos to 128000
INFO:gguf.vocab:Setting special token type eos to 128009
INFO:gguf.vocab:Setting special token type pad to 128256
INFO:gguf.vocab:Setting chat_template to {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
' }}{% endif %}
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-00002.safetensors'
INFO:hf-to-gguf:token_embd.weight, torch.float16 --> F16, shape = {4096, 128257}
INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.float16 --> F32, shape = {4096}
Traceback (most recent call last):
File "llama.cpp/convert-hf-to-gguf.py", line 3096, in <module>
main()
File "llama.cpp/convert-hf-to-gguf.py", line 3091, in main
model_instance.write()
File "llama.cpp/convert-hf-to-gguf.py", line 330, in write
self.write_tensors()
File "llama.cpp/convert-hf-to-gguf.py", line 1402, in write_tensors
super().write_tensors()
File "llama.cpp/convert-hf-to-gguf.py", line 267, in write_tensors
for new_name, data in ((n, d.squeeze().numpy()) for n, d in self.modify_tensors(data_torch, name, bid)):
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "llama.cpp/convert-hf-to-gguf.py", line 1399, in modify_tensors
return [(self.map_tensor_name(name), data_torch)]
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "llama.cpp/convert-hf-to-gguf.py", line 185, in map_tensor_name
raise ValueError(f"Can not map tensor {name!r}")
ValueError: Can not map tensor 'model.layers.0.mlp.down_proj.qweight'
What happened?
When trying to convert my quantized LoRA model from HF to GGUF using convert-hf-to-gguf.py I get the below error:
ValueError: Can not map tensor 'model.layers.0.mlp.down_proj.qweight'
Expected behavior: Conversion should have succeeded.
Name and Version
convert-hf-to-gguf.py, python 3.11.6
What operating system are you seeing the problem on?
No response
Relevant log output