You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am getting the same error but when I am using the second model I am getting this error: ggml_metal_graph_compute_block_invoke: error: node 909, op = POOL_2D not implemented
GGML_ASSERT: ggml/src/ggml-metal.m:2825: false
zsh: abort ./llama-llava-cli -m ../MobileVLM_V2-1.7B/ggml-model-q4-k.gguf --mmproj -p
I tried two gguf conversion on M2 ultra (metal) but no luck. I converted them myself and still the same error.
Here is the first model I tried:
https://huggingface.co/guinmoon/MobileVLM-1.7B-GGUF
Error:
Second model I tried:
https://huggingface.co/ZiangWu/MobileVLM_V2-1.7B-GGUF
Error:
The text was updated successfully, but these errors were encountered: