up

Author: Vaibhavs10

docs/inference-providers/guides/vscode-copilot.md

@@ -1,23 +1,23 @@
 # 🤗 Hugging Face Inference Providers for VS Code Copilot
 
-![Demo](assets/demo.gif)
+![Demo](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/demo.gif)
 
 <!-- Place demo.gif at docs/inference-providers/guides/assets/demo.gif -->
 
-Bring SoTA open‑source models to VS Code Copilot Chat with [Hugging Face Inference Providers](https://huggingface.co/docs/inference-providers/index), built on the [Language Model Chat Provider API](https://code.visualstudio.com/api/extension-guides/ai/language-model-chat-provider).
-
-## ✨ Why use the Hugging Face provider in Copilot
-- 4k+ open‑source LLMs with tool calling capabilities.
-- Single API to thousands of open‑source LLMs via providers like Groq, Cerebras, Together AI, SambaNova, and more.
-- Built for high availability (across providers) and low latency through world‑class providers.
-- No extra markup on provider rates.
+Bring SoTA open‑source LLMs to VS Code Copilot Chat with [Hugging Face Inference Providers](https://huggingface.co/docs/inference-providers/index), built on the [Language Model Chat Provider API](https://code.visualstudio.com/api/extension-guides/ai/language-model-chat-provider).
 
 ## ⚡ Quick start
+1. Install the HF Copilot Chat extension [here](#todo).
 1. Open VS Code's chat interface.
 2. Click the model picker and click "Manage Models...".
 3. Select "Hugging Face" provider.
 4. Provide your Hugging Face Token, you can get one in your [settings page](https://huggingface.co/settings/tokens/new?ownUserPermissions=inference.serverless.write&tokenType=fineGrained).
 5. Select the models you want to add to the model picker.
 
-💡 The free tier gives you a small amount of monthly inference credits to start building and experimenting. Upgrade to [Hugging Face PRO](https://huggingface.co/pro) for $2 in monthly credits plus pay‑as‑you‑go access across all providers!
+## ✨ Why use the Hugging Face provider in Copilot
+- 4k+ open‑source LLMs with tool calling capabilities.
+- Single API to thousands of open‑source LLMs via providers like Groq, Cerebras, Together AI, SambaNova, and more.
+- Built for high availability (across providers) and low latency through world‑class providers.
+- No extra markup on provider rates.
 
+💡 The free tier gives you a small amount of monthly inference credits to experiment. Upgrade to [Hugging Face PRO](https://huggingface.co/pro) or [Enterprise](https://huggingface/enterprise) for $2 in monthly credits plus pay‑as‑you‑go access across all providers!