Replies: 1 comment
-
I found the issue here, it was a problem with the conversion to GGUF that caused this issue |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi I have a Mac with an M2. I installed the llama-cpp-python with the latest version installed (0.1.83) using:
'CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install -U llama-cpp-python --no-cache-dir'
When I run against a gguf formatted llama 2 model, using:
export N_GQA=8 && python3 -m llama_cpp.server --model $MODEL --n_gpu_layers 38
I get the error:
error loading model: create_tensor: tensor 'blk.0.attn_k.weight' has wrong shape; expected 8192, 8192, got 8192, 1024, 1, 1 llama_load_model_from_file: failed to load model
Anyone know how to resolve this?
Beta Was this translation helpful? Give feedback.
All reactions