diff --git a/README.md b/README.md index 1890219..2c1d326 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,7 @@ # llama-swap +![llama-swap header image](header.jpeg) + [llama.cpp's server](https://github.com/ggerganov/llama.cpp/tree/master/examples/server) can't swap models, so let's swap llama-server instead! llama-swap is a proxy server that sits in front of llama-server. When a request for `/v1/chat/completions` comes in it will extract the `model` requested and change the underlying llama-server automatically. diff --git a/header.jpeg b/header.jpeg new file mode 100644 index 0000000..d0a3273 Binary files /dev/null and b/header.jpeg differ