add Docker example

README.md

@@ -10,4 +10,32 @@ tags:
 ---
 
 # phate334/multilingual-e5-large-gguf
-This model was converted to GGUF format from [`intfloat/multilingual-e5-large`](https://huggingface.co/intfloat/multilingual-e5-large) using llama.cpp.
+This model was converted to GGUF format from [`intfloat/multilingual-e5-large`](https://huggingface.co/intfloat/multilingual-e5-large) using llama.cpp.
+
+## Run it
+
+- Deploy using Docker
+
+```bash
+$ docker run -p 8080:8080 -v ./multilingual-e5-large-q4_k_m.gguf:/multilingual-e5-large-q4_k_m.gguf ghcr.io/ggerganov/llama.cpp:server--b1-4b9afbb --host 0.0.0.0 --embedding -m /multilingual-e5-large-q4_k_m.gguf
+```
+
+or Docker Compose
+
+```yaml
+services:
+  e5-f16:
+    image: ghcr.io/ggerganov/llama.cpp:server--b1-4b9afbb
+    ports:
+      - 8080:8080
+    volumes:
+      - ./multilingual-e5-large-f16.gguf:/multilingual-e5-large-f16.gguf
+    command: --host 0.0.0.0 --embedding -m /multilingual-e5-large-f16.gguf
+  e5-q4:
+    image: ghcr.io/ggerganov/llama.cpp:server--b1-4b9afbb
+    ports:
+      - 8081:8080
+    volumes:
+      - ./multilingual-e5-large-q4_k_m.gguf:/multilingual-e5-large-q4_k_m.gguf
+    command: --host 0.0.0.0 --embedding -m /multilingual-e5-large-q4_k_m.gguf
+```