📝 improve free trial docs

docs/docs/reference/Model Providers/anthropicllm.md

@@ -1,20 +1,18 @@
-# AnthropicLLM
+# Anthropic
 
-To setup Anthropic, add the following to your `config.json` file:
+To setup Anthropic, obtain an API key from [here](https://www.anthropic.com/api) and add the following to your `config.json` file:
 
 ```json title="~/.continue/config.json"
 {
   "models": [
     {
       "title": "Anthropic",
       "provider": "anthropic",
-      "model": "claude-2",
+      "model": "claude-3-opus-20240229",
       "apiKey": "YOUR_API_KEY"
     }
   ]
 }
 ```
 
-Claude 2 is not yet publicly released. You can request early access [here](https://www.anthropic.com/earlyaccess).
-
 [View the source](https://github.com/continuedev/continue/blob/main/core/llm/llms/Anthropic.ts)

docs/docs/reference/Model Providers/freetrial.md

@@ -1,24 +1,72 @@
-# FreeTrial
+# Free Trial
 
-With the `FreeTrial` provider, new users can try out Continue with GPT-4 using a proxy server that securely makes calls to OpenAI using our API key. Continue should just work the first time you install the extension in VS Code.
+The `"free-trial"` provider lets new users try out Continue with GPT-4, Llama3, Claude 3, and other models using a proxy server that securely makes API calls to these services. Continue should just work the first time you install the extension.
 
-Once you are using Continue regularly though, you will need to add an OpenAI API key that has access to GPT-4 by following these steps:
+While the Continue extension is always free to use, we cannot support infinite free LLM usage for all of our users. You will eventually need to either:
+
+1. Select an open-source model to use for free locally, or
+2. Add your own API key for OpenAI, Anthropic, or another LLM provider
+
+## Options
+
+### 🦙 Ollama (free, local)
+
+Ollama is a local service that makes it easy to run language models on your laptop.
+
+1. Download Ollama from https://ollama.ai
+2. Open `~/.continue/config.json`. You can do this by clicking the gear icon in the bottom right corner of the Continue sidebar
+3. Add the following to your `config.json`:
+
+```json title="~/.continue/config.json"
+{
+  "models": [
+    {
+      "title": "Llama3 8b",
+      "provider": "ollama",
+      "model": "llama3:8b"
+    }
+  ]
+}
+```
+
+### ⚡️ Groq (extremely fast)
+
+Groq provides lightning fast inference for open-source LLMs like Llama3, up to twice as fast as through other providers.
+
+1. Obtain an API key from https://console.groq.com
+2. Add the following to your `config.json`:
+
+```json title="~/.continue/config.json"
+{
+  "models": [
+    {
+      "title": "Llama3 70b",
+      "provider": "groq",
+      "model": "llama3-70b",
+      "apiKey": "YOUR_API_KEY"
+    }
+  ]
+}
+```
+
+### ✨ OpenAI (highly capable)
 
 1. Copy your API key from https://platform.openai.com/account/api-keys
-2. Open `~/.continue/config.json`. You can do this by using the '/config' command in Continue
-3. Change the LLM to look like this:
+2. Add the following to your `config.json`:
 
 ```json title="~/.continue/config.json"
 {
   "models": [
     {
-      "title": "GPT-4",
+      "title": "GPT-4-Turbo",
       "provider": "openai",
-      "model": "gpt-4",
+      "model": "gpt-4-turbo",
       "apiKey": "YOUR_API_KEY"
     }
   ]
 }
 ```
 
-[View the source](https://github.com/continuedev/continue/blob/main/core/llm/llms/FreeTrial.ts)
+### ⏩ Other options
+
+The above were only a few examples, but Continue can be used with any LLM or provider. You can find [a full list of providers here](../../setup/select-provider.md).

docs/docs/reference/Model Providers/ollama.md

@@ -1,16 +1,14 @@
 # Ollama
 
-[Ollama](https://ollama.ai/) is an application for Mac and Linux that makes it easy to locally run open-source models, including Llama-2. Download the app from the website, and it will walk you through setup in a couple of minutes. You can also read more in their [README](https://github.com/jmorganca/ollama). Continue can then be configured to use the `Ollama` LLM class:
+[Ollama](https://ollama.ai/) is an application for Mac, Windows, and Linux that makes it easy to locally run open-source models, including Llama3. Download the app from the website, and it will walk you through setup in a couple of minutes. You can also read more in their [README](https://github.com/ollama/ollama). Continue can then be configured to use the `"ollama"` provider:
 
 ```json title="~/.continue/config.json"
 {
   "models": [
     {
       "title": "Ollama",
       "provider": "ollama",
-      "model": "llama2-7b",
-      "completionOptions": {},
-      "apiBase": "http://localhost:11434"
+      "model": "llama3:8b"
     }
   ]
 }
@@ -38,7 +36,7 @@ If you need to send custom headers for authentication, you may use the `requestO
     {
       "title": "Ollama",
       "provider": "ollama",
-      "model": "llama2-7b",
+      "model": "llama3:8b",
       "requestOptions": {
         "headers": {
           "Authorization": "Bearer xxx"