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
Repository: https://huggingface.co/Sweaterdog/Andy‑4

📊 Training Regimen

Andy‑4‑base‑1 dataset
- Epochs: 2
- Learning Rate: 5e-5
- Dataset Size: 47.4k
Andy‑4‑base-2 dataset
- Epochs: 2
- Learning Rate: 7e-5
- Dataset Size: 49.2k
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

Visit Andy-4 on Ollama
Copy the command after choosing model type / quantization
Run the command in the terminal
Set the profile's model to be what you installed, such as ollama/sweaterdog/andy-4:tiny-q8_0

2. Manual Download & Modelfile

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.
Edit

Change

FROM YOUR/PATH/HERE

to

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

Create
ollama create andy-4-tiny -f Modelfile

This registers the Andy‑4-tiny model locally.

📌 Acknowledgments

Click to expand

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

⚖️ License

See Andy 1.0 License.

This work uses data and models created by @Sweaterdog.

Sweaterdog/Andy-4-tiny

🧠 Andy‑4-tiny 🐜