Update README.md

README.md

@@ -1,6 +1,165 @@
 ---
-license: apache-2.0
+datasets:
+- Sweaterdog/Andy-4-base-1
+- Sweaterdog/Andy-4-base-2
+- Sweaterdog/Andy-4-ft
+language:
+- en
+base_model:
+- unsloth/Llama3.1-8B
+tags:
+- gaming
+- minecraft
+- mindcraft
 ---
 
+# 🧠 Andy‑4 🧠
 
-# This is an empty repo, which will be the home of Andy-4 when finished
+**Andy‑4** is an 8 billion‑parameter specialist model tuned for Minecraft gameplay via the Mindcraft framework.  Trained on a single RTX 3090 over **three weeks**, Andy‑4 delivers advanced reasoning, multi‑step planning, and robust in‑game decision‑making.
+
+> ⚠️ **Certification:**  
+> Andy‑4 is **not yet certified** by the Mindcraft developers. Use in production at your own discretion.
+
+---
+
+## 🔍 Model Specifications
+
+- **Parameters:** 8 B  
+- **Training Hardware:** 1 × NVIDIA RTX 3090  
+- **Duration:** ~3 weeks total  
+- **Data Volumes:**  
+  - **Messages:** 179 384  
+  - **Tokens:** 425 535 198  
+  - **Conversations:** 62 149  
+
+- **Base Architecture:** Llama 3.1 8B  
+- **License:** [Andy 1.1 License](LICENSE)  
+- **Repository:** https://huggingface.co/Sweaterdog/Andy‑4
+
+---
+
+## 📊 Training Regimen
+
+1. **Andy‑4‑base‑1** dataset  
+   - **Epochs:** 2  
+   - **Learning Rate:**   7e-5
+
+2. **Andy‑4‑base‑2** dataset  
+   - **Epochs:** 4  
+   - **Learning Rate:**   3e-7
+
+3. **Fine‑tune (FT) dataset**  
+   - **Epochs:** 2.5  
+   - **Learning Rate:** 2e-5
+
+- **Optimizer:** AdamW_8bit with cosine decay  
+- **Quantization:** 4‑bit (`bnb-4bit`) for inference
+- **Warm Up Steps:** 0.1% of each dataset
+
+---
+
+## 🚀 Installation
+
+### 1. Quick Hugging Face + Ollama *(Not recommended)*
+
+1. On the HF model page, click **Use this model → Ollama**.  
+2. Choose your quantization (see table).  
+3. Copy and run the provided `ollama run` command.
+
+| Quantization | VRAM Required |
+|--------------|---------------|
+| F16          | 16 GB+        |
+| Q5_K_M       | 8 GB+         |
+| Q4_K_M       | 6–8 GB        |
+| Q3_K_M       | 6 GB (low)    |
+| Q2_K         | 4–6 GB (ultra)|
+
+If you lack a GPU, check the [Mindcraft Discord guide](https://ptb.discord.com/channels/1303399789995626667/1347027684768878644/1347027684768878644) for free cloud setups.
+
+---
+
+### 2. Manual Download & Modelfile
+
+1. **Download**  
+   - From the HF **Files** tab, grab your chosen `.GGUF` quant weights (e.g. `Andy-4.Q4_K_M.gguf`).  
+   - Download the provided `Modelfile`.
+
+     Follow this table to choose your quantization, this is for a 8192 context window, the default, as well as a non-quantized context window.
+
+| Quantization | VRAM Required |
+|--------------|---------------|
+| F16          | 16 GB+        |
+| Q5_K_M       | 8 GB+         |
+| Q4_K_M       | 6–8 GB        |
+| Q3_K_M       | 6 GB (low)    |
+| Q2_K         | 4–6 GB (ultra)|
+
+2. **Edit**
+
+   Change
+   ```text
+   FROM YOUR/PATH/HERE
+   ```
+   to
+   ```text
+   FROM /path/to/Andy-4.Q4_K_M.gguf
+   ```
+  *Optional*:
+  Increase the parameter `num_ctx` to a higher value for longer conversations if you:
+
+  **A.** Have extra VRAM
+
+  **B.** Quantized the context window
+
+  **C.** Can use a smaller model
+
+3. **Create**  
+   ```bash
+   ollama create andy-4 -f Modelfile
+   ```
+
+This registers the **Andy‑4** model locally.
+
+---
+
+## 🔧 Context‑Window Quantization
+
+To lower VRAM use for context windows:
+
+#### **Windows**
+
+1. Close Ollama.  
+2. In **System Properties → Environment Variables**, add:  
+   ```text
+   OLLAMA_FLASH_ATTENTION=1  
+   OLLAMA_KV_CACHE_TYPE=q8_0   # or q4_0 for extra savings, but far more unstable
+   ```  
+3. Restart Ollama.
+
+#### **Linux/macOS**
+
+```bash
+export OLLAMA_FLASH_ATTENTION=1
+export OLLAMA_KV_CACHE_TYPE="q8_0"   # or "q4_0", but far more unstable
+ollama serve
+```
+
+---
+
+## 📌 Acknowledgments
+
+<details>
+<summary>Click to expand</summary>
+
+- **Data & Models by:** @Sweaterdog  
+- **Framework:** Mindcraft (https://github.com/kolbytn/mindcraft)  
+- **LoRA Weights:** https://huggingface.co/Sweaterdog/Andy-4-LoRA  
+</details>
+
+---
+
+## ⚖️ License
+
+See [Andy 1.1 License](LICENSE).  
+
+*This work uses data and models created by @Sweaterdog.*