Is it working ?
#1
by
Suppenkoch
- opened
llama_model_load: error loading model: check_tensor_dims: tensor 'blk.0.attn_qkv.weight' has wrong shape; expected 4096, 4608, got 4096, 5120, 1, 1
llama_load_model_from_file: failed to load model
I tried Ollama, LlamaCpp and KoboldCpp. Always the same error message.
Yep. me too.. but the conversion seems fine.. I opened an issue on github.. we'll see if the problem is in the conversion or execution.