Spaces:

ggml-org

/

gguf-my-repo

like 1.09k

Running on A10G

Hello,

I'm encountering an issue while converting the netease-youdao/Qwen-7B-QAnything model to GGUF format using the Huggingface Space for automatic model conversion. Detailed information is as follows:

• Model: netease-youdao/Qwen-7B-QAnything
• Quantization Methods attempted: Q4_K_M, Q8_0 (both resulted in the same error)

Here is the complete error trace:

Error: Error converting to fp16: b'INFO:hf-to-gguf:Loading model: Qwen-7B-QAnything\n
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only\n
INFO:hf-to-gguf:Set model parameters\n
Traceback (most recent call last):\n
  File "/home/user/app/llama.cpp/convert-hf-to-gguf.py", line 2546, in \n
    main()\n
  File "/home/user/app/llama.cpp/convert-hf-to-gguf.py", line 2528, in main\n
    model_instance.set_gguf_parameters()\n
  File "/home/user/app/llama.cpp/convert-hf-to-gguf.py", line 1576, in set_gguf_parameters\n
    self.gguf_writer.add_context_length(self.hparams["max_position_embeddings"])\n
KeyError: 'max_position_embeddings'\n'

It appears the script is expecting a max_position_embeddings parameter in the model's hparams, which is not present. This raises a KeyError.

Could you please advise on how to address this issue? Any help or guidance would be greatly appreciated.

Thank you!