Revise local model usage instructions in README

README.md

@@ -81,11 +81,8 @@ You can configure the agent's name, model, and prompts in their profile like `an
 
 For more comprehensive model configuration and syntax, see [Model Specifications](#model-specifications).
 
-For local models we support [ollama](https://ollama.com/) and we provide our own finetuned models for you to use. 
-To install our models, install ollama and run the following terminal command:
-```bash
-ollama pull sweaterdog/andy-4:micro-q8_0 && ollama pull embeddinggemma
-```
+For local models, we recommend you use **LM Studio** for the Andy series of models. Ollama breaks current models, and should be avoided.
+Please see our [huggingface page for more info.](https://huggingface.co/collections/Mindcraft-CE)
 
 ## Online Servers
 To connect to online servers your bot will need an official Microsoft/Minecraft account. You can use your own personal one, but will need another account if you want to connect too and play with it. To connect, change these lines in `settings.js`:

profiles/andy-4.2.json

@@ -0,0 +1,11 @@
+{
+    "name": "andy_4_2",
+    "model": {
+        "api": "lmstudio",
+        "model": "andy-4.2"
+    },
+    "embedding": {
+        "api": "lmstudio",
+        "model": "text-embedding-nomic-embed-text-v1.5"
+    }
+}

settings.js

@@ -20,7 +20,7 @@ const settings = {
         // "./profiles/mistral.json",
         // "./profiles/deepseek.json",
         // "./profiles/mercury.json",
-        // "./profiles/andy-4.json", // Supports up to 75 messages!
+        // "./profiles/andy-4.2.json",
 
         // using more than 1 profile requires you to /msg each bot indivually
         // individual profiles override values from the base profile