Embeddings doesn't work

#1
by Jamshaid89 - opened

When I start llama-server with --embeddings argument it fails to load.

also this command results in error
./llama-cli --hf-repo philip-weyer/Qwen3-VL-Embedding-8B-Q4_K_M-GGUF --hf-file qwen3-vl-embedding-8b-q4_k_m.gguf -p "The meaning to life and the universe is"

UPDATE:

I have fixed the problem. The issue was I was using older llama cpp build binaries. So try using latest build binaries. It solved my problem.

Jamshaid89 changed discussion status to closed

Sign up or log in to comment