TheBloke

/

Llama-2-70B-Chat-GGML

like 161

Trying to use convert-llama-ggmlv3-to-gguf.py from llama-cpp, I am unable to convert the model llama-2-70b-chat.ggmlv3.q4_K_M.bin to gguf format in order to use with llama-cpp.

Error:
"""

• Preparing to save GGUF file
• Adding model parameters and KV items
• Adding 32000 vocab item(s)
• Adding 723 tensor(s)
  Traceback (most recent call last):
  File "/llm/barha/llama.cpp/convert-llama-ggmlv3-to-gguf.py", line 345, in
  main()
  File "/llm/barha/llama.cpp/convert-llama-ggmlv3-to-gguf.py", line 341, in main
  converter.save()
  File "/llm/barha/llama.cpp/convert-llama-ggmlv3-to-gguf.py", line 165, in save
  self.add_tensors(gguf_writer)
  File "/llm/barha/llama.cpp/convert-llama-ggmlv3-to-gguf.py", line 273, in add_tensors
  mapped_name = nm.get(name)
  AttributeError: 'TensorNameMap' object has no attribute 'get'
  """