Error loading the model with LM Studio.

#1
by FlameF0X - opened
Failed to load last used model.

Failed to load model

error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'qwen3'
Romarchive AI org
edited Jan 27

Hello, as I understand this error is caused by the model, not a quantization. But still, I will remain this open until it will work. (I will update you if there will be fix)

Romarchive AI org

Main problem is that BPE tokenizer is not recognized in llama.cpp, and I had to force qwen3

WARNING:hf-to-gguf:**************************************************************************************
WARNING:hf-to-gguf:** WARNING: The BPE pre-tokenizer was not recognized!
WARNING:hf-to-gguf:**          There are 2 possible reasons for this:
WARNING:hf-to-gguf:**          - the model has not been added to convert_hf_to_gguf_update.py yet
WARNING:hf-to-gguf:**          - the pre-tokenization config has changed upstream
WARNING:hf-to-gguf:**          Check your model files and convert_hf_to_gguf_update.py and update them accordingly.
WARNING:hf-to-gguf:** ref:     https://github.com/ggml-org/llama.cpp/pull/6920
WARNING:hf-to-gguf:**
WARNING:hf-to-gguf:** chkhsh:  7a5e1981344bd694e1f742be597f5bcc3f02d5e5bbb45f5a8a7a4b89b12ac37d
WARNING:hf-to-gguf:**************************************************************************************

oh, okay.

Romarchive AI org

I found the fix. Requantizing now and uploading.

Romarchive AI org

fixed

sapbot changed discussion status to closed

Sign up or log in to comment