diff --git a/content/spin/v1/ai-sentiment-analysis-api-tutorial.md b/content/spin/v1/ai-sentiment-analysis-api-tutorial.md
index bfd07716d..b585db0c4 100644
--- a/content/spin/v1/ai-sentiment-analysis-api-tutorial.md
+++ b/content/spin/v1/ai-sentiment-analysis-api-tutorial.md
@@ -162,8 +162,8 @@ Next, we need to create the appropriate folder structure from within the applica
 
 ```bash
 # llama2-chat
-$ mkdir -p .spin/ai-models
-$ cd .spin/ai-models
+$ mkdir -p .spin/ai-models/llama
+$ cd .spin/ai-models/llama
 $ wget https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/resolve/a17885f653039bd07ed0f8ff4ecc373abf5425fd/llama-2-13b-chat.ggmlv3.q3_K_L.bin
 $ mv llama-2-13b-chat.ggmlv3.q3_K_L.bin llama2-chat
 ```
@@ -174,7 +174,8 @@ $ mv llama-2-13b-chat.ggmlv3.q3_K_L.bin llama2-chat
 tree .spin
 .spin
 └── ai-models
-    └── llama2-chat
+    └── llama
+        └── llama2-chat
 ```
 
 **codellama-instruct example download**
@@ -185,8 +186,8 @@ tree .spin
 
 ```bash
 # codellama-instruct
-$ mkdir -p .spin/ai-models
-$ cd .spin/ai-models
+$ mkdir -p .spin/ai-models/llama
+$ cd .spin/ai-models/llama
 $ wget https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GGML/resolve/b3dc9d8df8b4143ee18407169f09bc12c0ae09ef/codellama-13b-instruct.ggmlv3.Q3_K_L.bin
 $ mv codellama-13b-instruct.ggmlv3.Q3_K_L.bin codellama-instruct
 ```
@@ -197,7 +198,8 @@ $ mv codellama-13b-instruct.ggmlv3.Q3_K_L.bin codellama-instruct
 tree .spin
 .spin
 └── ai-models
-    └── codellama-instruct
+    └── llama
+        └── codellama-instruct
 ```
 
 **all-minilm-l6-v2 example download**
diff --git a/content/spin/v1/serverless-ai-api-guide.md b/content/spin/v1/serverless-ai-api-guide.md
index 89e3f2f15..ee66ef8e1 100644
--- a/content/spin/v1/serverless-ai-api-guide.md
+++ b/content/spin/v1/serverless-ai-api-guide.md
@@ -38,7 +38,7 @@ ai_models = ["codellama-instruct"]
 By default, the Spin framework will expect any already trained model files (which are configured as per the previous section) to be downloaded by the user and made available inside a `.spin/ai-models/` file path of a given application. For example:
 
 ```bash
-code-generator-rs/.spin/ai-models/codellama-instruct
+code-generator-rs/.spin/ai-models/llama/codellama-instruct
 ```
 
 See the [serverless AI Tutorial](./ai-sentiment-analysis-api-tutorial) documentation for more concrete examples of implementing the Fermyon Serverless AI API, in your favorite language.
diff --git a/content/spin/v1/serverless-ai-hello-world.md b/content/spin/v1/serverless-ai-hello-world.md
index ca0e07527..755545625 100644
--- a/content/spin/v1/serverless-ai-hello-world.md
+++ b/content/spin/v1/serverless-ai-hello-world.md
@@ -336,7 +336,7 @@ Available Routes:
 hello-world: https://hello-world-XXXXXX.fermyon.app (wildcard)
 ```
  
-The app’s manifest file reads the line `ai-models = ["llama2-chat"]` and uses that model in the cloud. For any changes to take effect in the app, it needs to be re-deployed to the cloud.
+The app’s manifest file reads the line `ai_models = ["llama2-chat"]` and uses that model in the cloud. For any changes to take effect in the app, it needs to be re-deployed to the cloud.
  
 **Using the Cloud-GPU plugin to test locally**
  
diff --git a/content/spin/v2/ai-sentiment-analysis-api-tutorial.md b/content/spin/v2/ai-sentiment-analysis-api-tutorial.md
index 71f5edb3e..62c4660ca 100644
--- a/content/spin/v2/ai-sentiment-analysis-api-tutorial.md
+++ b/content/spin/v2/ai-sentiment-analysis-api-tutorial.md
@@ -183,8 +183,8 @@ Next, we need to create the appropriate folder structure from within the applica
 
 ```bash
 # llama2-chat
-$ mkdir -p .spin/ai-models
-$ cd .spin/ai-models
+$ mkdir -p .spin/ai-models/llama
+$ cd .spin/ai-models/llama
 $ wget https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/resolve/a17885f653039bd07ed0f8ff4ecc373abf5425fd/llama-2-13b-chat.ggmlv3.q3_K_L.bin
 $ mv llama-2-13b-chat.ggmlv3.q3_K_L.bin llama2-chat
 ```
@@ -195,7 +195,8 @@ $ mv llama-2-13b-chat.ggmlv3.q3_K_L.bin llama2-chat
 tree .spin
 .spin
 └── ai-models
-    └── llama2-chat
+    └── llama
+        └── llama2-chat
 ```
 
 **codellama-instruct example download**
@@ -206,8 +207,8 @@ tree .spin
 
 ```bash
 # codellama-instruct
-$ mkdir -p .spin/ai-models
-$ cd .spin/ai-models
+$ mkdir -p .spin/ai-models/llama
+$ cd .spin/ai-models/llama
 $ wget https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-GGML/resolve/b3dc9d8df8b4143ee18407169f09bc12c0ae09ef/codellama-13b-instruct.ggmlv3.Q3_K_L.bin
 $ mv codellama-13b-instruct.ggmlv3.Q3_K_L.bin codellama-instruct
 ```
@@ -218,7 +219,8 @@ $ mv codellama-13b-instruct.ggmlv3.Q3_K_L.bin codellama-instruct
 tree .spin
 .spin
 └── ai-models
-    └── codellama-instruct
+    └── llama
+        └── codellama-instruct
 ```
 
 **all-minilm-l6-v2 example download**
diff --git a/content/spin/v2/serverless-ai-api-guide.md b/content/spin/v2/serverless-ai-api-guide.md
index 0aac891e9..097792326 100644
--- a/content/spin/v2/serverless-ai-api-guide.md
+++ b/content/spin/v2/serverless-ai-api-guide.md
@@ -37,7 +37,7 @@ ai_models = ["codellama-instruct"]
 By default, the Spin framework will expect any already trained model files (which are configured as per the previous section) to be downloaded by the user and made available inside a `.spin/ai-models/` file path of a given application. For example:
 
 ```bash
-code-generator-rs/.spin/ai-models/codellama-instruct
+code-generator-rs/.spin/ai-models/llama/codellama-instruct
 ```
 
 See the [serverless AI Tutorial](./ai-sentiment-analysis-api-tutorial) documentation for more concrete examples of implementing the Fermyon Serverless AI API, in your favorite language.
diff --git a/content/spin/v2/serverless-ai-hello-world.md b/content/spin/v2/serverless-ai-hello-world.md
index cc2c8a8ac..b58f8b0f8 100644
--- a/content/spin/v2/serverless-ai-hello-world.md
+++ b/content/spin/v2/serverless-ai-hello-world.md
@@ -332,7 +332,7 @@ Available Routes:
 hello-world: https://hello-world-XXXXXX.fermyon.app (wildcard)
 ```
  
-The app’s manifest file reads the line `ai-models = ["llama2-chat"]` and uses that model in the cloud. For any changes to take effect in the app, it needs to be re-deployed to the cloud.
+The app’s manifest file reads the line `ai_models = ["llama2-chat"]` and uses that model in the cloud. For any changes to take effect in the app, it needs to be re-deployed to the cloud.
  
 **Using the Cloud-GPU plugin to test locally**