You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: .github/steps/1-genai-prototype.md
+19-19Lines changed: 19 additions & 19 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -26,7 +26,7 @@ With GitHub Models, you can use GitHub Personal Access Tokens (PAT) to authentic
26
26
27
27
2. Click on **explore the full model catalog** to see the available models.
28
28
29
-

29
+

30
30
31
31
You will see a broad range of models listed in the catalog.
32
32
@@ -42,17 +42,17 @@ With GitHub Models, you can use GitHub Personal Access Tokens (PAT) to authentic
42
42
-**Model Abstract:** A brief description of the model and its capabilities.
43
43
-**Model Architecture:** The data used to train the model and their modalities for input and output _(text-image pairs)_, the model size _(parameters)_, model context length _(how much text the model can process at once)_, training date _(knowledge cut-off date/data freshness for the model)_, supported languages, and more.
5. After selecting a model and reviewing the model card, you can use the **Playground** to experiment with the model. The playground provides a user-friendly interface for testing the model's capabilities and understanding how it works.
You can directly send questions (prompts) to the model and see how it responds. Throughout the session, you can monitor the token usage and the model's response time at the top of the chat UI.
6. To check your token usage against your GitHub Models free quota (input/ output tokens, latency), click on the **Input: Output: Time** note at the top right of the chat UI to open Model usage insights.
7. Before going further, on the right side of the playground, switch from **Details** to **Parameters** to see the available parameters that you can adjust to change the model's behavior.
-**Max Tokens:** The maximum number of tokens the model can generate in response to a prompt. Adjusting this parameter can help control the length of the model's output.
@@ -95,13 +95,13 @@ With GitHub Models, you can use GitHub Personal Access Tokens (PAT) to authentic
95
95
96
96
Click on the **Compare** button at the top right of the playground.
In the example provided, you can compare the performance of a reasoning model and a conversation model on the same prompt to understand their strengths and limitations.
107
107
@@ -130,18 +130,18 @@ Now that you have a better understanding of the models from the GitHub Models pl
130
130
131
131
1. On the far right, click on **Use this model** and select**Language: JavaScript** and **SDK: Azure AI Inference SDK**.
## 📌 Exercise: Convert a hand-drawn sketch to a web page
143
143
144
-
1. Download the contoso website hand-drawn sketch from [this link](https://github.com/juliamuiruri4/JS-Journey-to-AI-Foundry/blob/assets/js-ai-journey-assets/contoso_layout_sketch.jpg), and save it `contoso_layout_sketch.jpg`in the same directory as your `sample.js` file.
144
+
1. Download the contoso website hand-drawn sketch from [this link](https://github.com/Azure-Samples/JS-AI-Build-a-thon/blob/assets/jsai-buildathon-assets/contoso_layout_sketch.jpg), and save it `contoso_layout_sketch.jpg`in the same directory as your `sample.js` file.
145
145
146
146
>**Note**
147
147
>
@@ -152,11 +152,11 @@ Now that you have a better understanding of the models from the GitHub Models pl
152
152
> **Note**
153
153
> You can use [GitHub Copilot](https://github.com/features/copilot) to help you with this task.
154
154
>
155
-
> 
155
+
> 
156
156
157
157
3. Run the code and check the output in the console.
@@ -166,7 +166,7 @@ The AI Toolkit in Visual Studio Code is a powerful extension that provides a set
166
166
167
167
2. Similar to GitHub Models, with the AI Toolkit now installed, you can browse through the catalog of available models, and use the **Playground** to experiment with the models, all on VS Code.
Let's execute the exercise above using the AI Toolkit in VS Code.
172
172
@@ -176,13 +176,13 @@ The AI Toolkit in Visual Studio Code is a powerful extension that provides a set
176
176
177
177
4. On the generated code, click on the **New file** icon to copy the generated code into a new file. Save it as `index.html`in the same directory as your `sample.js` file.
0 commit comments