gaianet

/

gte-Qwen1.5-7B-instruct-GGUF

like 4

Follow

Gaia 🌱 22

If just run like ./main --m path/to/this in llama.cpp. It will rasie error "GGML_ASSERT: examples/main/main.cpp:248: llama_add_eos_token(model) != 1", local llama.cpp works well with other GGUFs, eg.Qwen/Qwen1.5-7B-Chat-GGUF, make some notes pls.
thks