add llama 2 13b chat GGUF cpu only (#225)

substratusai · Aug 29, 2023 · 4d9b157 · 4d9b157
1 parent b3cb2b9
commit 4d9b157
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 1 deletion.
diff --git a/examples/llama2-13b-chat-gguf/server-cpu.yaml b/examples/llama2-13b-chat-gguf/server-cpu.yaml
@@ -0,0 +1,8 @@
+apiVersion: substratus.ai/v1
+kind: Server
+metadata:
+  name: llama2-13b-chat-gguf
+spec:
+  image: substratusai/model-server-llama-cpp:latest
+  model:
+    name: llama2-13b-chat-gguf
diff --git a/examples/llama2-13b-chat-gguf/server.yaml → ...ples/llama2-13b-chat-gguf/server-gpu.yaml b/examples/llama2-13b-chat-gguf/server.yaml → ...ples/llama2-13b-chat-gguf/server-gpu.yaml
@@ -3,7 +3,7 @@ kind: Server
 metadata:
   name: llama2-13b-chat-gguf
 spec:
-  image: substratusai/model-server-llama-cpp
+  image: substratusai/model-server-llama-cpp:latest-gpu
   model:
     name: llama2-13b-chat-gguf
   params: