lllama 13b chat GGML example with llama.cpp (#218)

substratusai · Aug 25, 2023 · d4f65da · d4f65da
1 parent d07052a
commit d4f65da
Show file tree

Hide file tree

Showing 2 changed files with 20 additions and 0 deletions.
diff --git a/examples/llama2-13b-chat-ggml/base-model.yaml b/examples/llama2-13b-chat-ggml/base-model.yaml
@@ -0,0 +1,9 @@
+apiVersion: substratus.ai/v1
+kind: Model
+metadata:
+  name: llama2-13b-chat-ggml
+spec:
+  image: substratusai/model-loader-huggingface
+  params:
+    name: TheBloke/Llama-2-13B-chat-GGML
+    files: "config.json,llama-2-13b-chat.ggmlv3.q2_K.bin"
diff --git a/examples/llama2-13b-chat-ggml/server.yaml b/examples/llama2-13b-chat-ggml/server.yaml
@@ -0,0 +1,11 @@
+apiVersion: substratus.ai/v1
+kind: Server
+metadata:
+  name: llama2-13b-chat-ggml
+spec:
+  image: substratusai/model-server-basaran
+  model:
+    name: llama2-13b-chat-ggml
+  resources:
+    gpu:
+      count: 1