|
|
--- |
|
|
datasets: |
|
|
- Sweaterdog/Andy-4-base |
|
|
- Sweaterdog/Andy-4-ft |
|
|
- Sweaterdog/Andy-base-2 |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- HuggingFaceTB/SmolLM2-360M-Instruct |
|
|
tags: |
|
|
- gaming |
|
|
- minecraft |
|
|
- mindcraft |
|
|
library_name: transformers |
|
|
--- |
|
|
|
|
|
# 🧠 Andy‑4-tiny 🐜 |
|
|
|
|
|
 |
|
|
|
|
|
|
|
|
**Andy‑4-tiny** is an 360 Million‑parameter specialist model tuned for Minecraft gameplay via the Mindcraft framework. |
|
|
**The Current version of Andy-4-tiny is** `Andy-4-tiny-0522`. |
|
|
|
|
|
> ⚠️ **Certification:** |
|
|
> Andy‑4 is **not yet certified** by the Mindcraft developers. Use in production at your own discretion. |
|
|
|
|
|
|
|
|
## 🔍 Model Specifications |
|
|
|
|
|
- **Parameters:** 360M |
|
|
- **Training Hardware:** 1 × NVIDIA RTX 3070 |
|
|
- **Duration:** ~ 36 hours total |
|
|
- **Data Volumes:** |
|
|
- **Messages:** 179,384 |
|
|
- **Tokens:** 425,535,198 |
|
|
- **Conversations:** 62,149 |
|
|
|
|
|
- **Base Architecture:** SmolLM2 |
|
|
- **License:** [Andy 1.0 License](LICENSE) |
|
|
- **Repository:** https://huggingface.co/Sweaterdog/Andy‑4 |
|
|
|
|
|
--- |
|
|
|
|
|
## 📊 Training Regimen |
|
|
|
|
|
1. **Andy‑4‑base‑1** dataset |
|
|
- **Epochs:** 2 |
|
|
- **Learning Rate:** 5e-5 |
|
|
- **Dataset Size:** 47.4k |
|
|
|
|
|
2. **Andy‑4‑base-2** dataset |
|
|
- **Epochs:** 2 |
|
|
- **Learning Rate:** 7e-5 |
|
|
- **Dataset Size:** 49.2k |
|
|
|
|
|
3. **Fine‑tune (FT) dataset** |
|
|
- **Epochs:** 2.5 |
|
|
- **Learning Rate:** 2e-5 |
|
|
- **Dataset Size:** 4.12k |
|
|
|
|
|
- **Optimizer:** AdamW_8bit with cosine decay |
|
|
- **Quantization:** 4‑bit (`bnb-4bit`) for inference |
|
|
- **Warm Up Steps:** 0.1% of each dataset |
|
|
|
|
|
--- |
|
|
|
|
|
## 🚀 Installation |
|
|
|
|
|
Andy-4-tiny is an Edge-case model, built to run on the CPU and use minimal ram. These are the requirements to *Run Them*, not to use them while Minecraft is also running. |
|
|
|
|
|
| Quantization | RAM Required | |
|
|
|--------------|---------------| |
|
|
| F16 | CPU 2GB | |
|
|
| Q8_0 | CPU 1GB | |
|
|
| Q4_K_M | CPU 0.8GB | |
|
|
|
|
|
### 1. Installation directly on Ollama |
|
|
|
|
|
1. Visit [Andy-4 on Ollama](https://ollama.com/Sweaterdog/Andy-4) |
|
|
2. Copy the command after choosing model type / quantization |
|
|
3. Run the command in the terminal |
|
|
4. Set the profile's model to be what you installed, such as `ollama/sweaterdog/andy-4:tiny-q8_0` |
|
|
|
|
|
### 2. Manual Download & Modelfile |
|
|
|
|
|
1. **Download** |
|
|
- From the HF **Files** tab, grab your chosen `.GGUF` quant weights (e.g. `Andy-4-tiny.Q4_K_M.gguf`). |
|
|
- Download the provided `Modelfile`. |
|
|
|
|
|
|
|
|
2. **Edit** |
|
|
|
|
|
Change |
|
|
```text |
|
|
FROM YOUR/PATH/HERE |
|
|
``` |
|
|
to |
|
|
```text |
|
|
FROM /path/to/Andy-4-tiny.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-tiny -f Modelfile |
|
|
``` |
|
|
|
|
|
This registers the **Andy‑4-tiny** model locally. |
|
|
|
|
|
--- |
|
|
|
|
|
## 📌 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 |
|
|
- *Explicit credit is not granted to Meta since this model was trained off of a slightly different architecture, from [DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) |
|
|
</details> |
|
|
|
|
|
--- |
|
|
|
|
|
## ⚖️ License |
|
|
|
|
|
See [Andy 1.0 License](LICENSE). |
|
|
|
|
|
*This work uses data and models created by @Sweaterdog.* |
