1
2{
3 "inputs": "A plain old prompt with nothing else"
4}
Hello! I wrote a simple container that allows for easy running of llama-cpp-python with GGUF models. My goal here was a cheap way to play with Gemma, but then I thought maybe i'd share just in case it's helpful. I'll probably make a bunch of these, so if you have any requests for GGUF or otherwise quantized Llama.cpp models to become inference endpoints, please feel free to reach out!
I used the excellent quant by
lmstudio-ai/gemma-2b-it-GGUF,
Just kidding, it's sam att samuellmeyers DOT... com