Open sorasoras opened 1 month ago
What was the full command you were using and what version if possible?
What was the full command you were using and what version if possible?
llamafile-0.8.4 .\llamafile-0.8.4.exe -m .\sakura0.92_1.0_IQ4XS.gguf -ngl 99 it's a qwen2 14B model
llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'qwen2' llama_load_model_from_file: failed to load model
I tried to load this model using llamafile but it seems working on llama cpp but not llamafile