bug: Unable to run Ling 3.0 Tiny model on llama.cpp turbo quant engine

[aryapratham1601-sketch]

App Version - v2.0.7

Describe the Bug

Failed to load the model

The model could not be started. The model process encountered an unexpected error.
0.00.096.626 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the '-lv N' CLI arg) 0.00.097.328 I srv init: The UI is disabled 0.00.097.330 I srv init: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.099.861 I srv load_model: loading model '/Users/user/Library/Application Support/Atomic Chat/data/llamacpp/models/bloomer010/Ling-3_0-tiny-Q4_K_M/model.gguf' 0.00.212.233 W load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
0.00.254.767 E llama_model_load: error loading model: check_tensor_dims: tensor 'blk.0.ssm_f.weight' not found 0.00.254.896 E llama_model_load_from_file_impl: failed to load model 0.00.254.899 E cmn common_init_: failed to load model '/Users/user/Library/Application Support/Atomic Chat/data/llamacpp/models/bloomer010/Ling-3_0-tiny-Q4_K_M/model.gguf' 0.00.254.900 E srv load_model: failed to load model, '/Users/user/Library/Application Support/Atomic Chat/data/llamacpp/models/bloomer010/Ling-3_0-tiny-Q4_K_M/model.gguf' 0.00.254.902 I srv operator(): operator(): cleaning up before exit... 0.00.255.655 E srv llama_server: exiting due to model loading error
[LLAMA_CPP_PROCESS_ERROR]

Short Description

llama_model_load: error loading model: check_tensor_dims: tensor 'blk.0.ssm_f.weight' not found

Screenshots / Logs

Operating System

• [x ] MacOS
• Windows
• Linux

[dtorey-d]

@aryapratham1601-sketch hey! thanks for the report - we'll look into it with the team, i think the issue is with the llama.cpp version