llama.cpp can not load this gguf

#1
by keelsike - opened

error loading model: unknown model architecture: 'qwen2'
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model 'models/qwen1_5-14b-chat-q5_k_m.gguf'

This architecture was added there only in January,
so update your llama.cpp.
I am already successfully using llama.cpp with this Q5_K_M gguf.
BTW, the latest text-generation-webui is bundled with recent enough llama.cpp.

Thanks, its OK now.

JustinLin610 changed discussion status to closed

Sign up or log in to comment