error when to try this gguf
#3
by
cloudyu
- opened
llama_model_loader: - type f32: 321 tensors
llama_model_loader: - type q8_0: 450 tensors
llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'deepseek-r1-qwen'
llama_load_model_from_file: failed to load model
common_init_from_params: failed to load model '/Users/yuhai/Downloads/DeepSeek-R1-Distill-Qwen-32B-Q8_0.gguf'
command:
./llama.cpp/llama-cli
--model ~/Downloads/DeepSeek-R1-Distill-Qwen-32B-Q8_0.gguf
--threads 16
--prompt '<｜User｜>What is 1+1?<｜Assistant｜>'
llama.cpp build: 4153 (6dfcfef0) with Apple clang version 15.0.0 (clang-1500.3.9.4) for arm64-apple-darwin23.5.0
you may need to update llama.cpp >= b4514
you may need to update llama.cpp >= b4514
thanks, solved by update code
cloudyu
changed discussion status to
closed