not working with llama-b11345
0.00.159.996 I srv load_model: loading model './models/Laya-BF16.gguf'
0.00.160.001 I srv load_model: local path './models/Laya-BF16.gguf'
0.00.160.014 I cmn common_init_: fitting params to device memory ...
0.00.160.015 I cmn common_init_: (for bugs during this step try to reproduce them with -fit off, or provide --verbose logs if the bug only occurs with -fit on)
0.00.160.053 I common_params_fit_impl: getting device memory data for initial parameters:
0.00.209.884 E llama_model_load: error loading model: check_tensor_dims: tensor 'blk.28.ffn_up.weight' has wrong shape; expected 1024, 5248, got 1024, 4096, 1, 1
0.00.209.889 E llama_model_load_from_file_impl: failed to load model
0.00.209.910 E common_fit_params: encountered an error while trying to fit params to free device memory: failed to load model
new version llama.cpp is working now