Instructions to use tampakwill/AWA-40M-Micro-LLM-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tampakwill/AWA-40M-Micro-LLM-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tampakwill/AWA-40M-Micro-LLM-GGUF",
	filename="AWA-40M-Daging-V1-F32.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tampakwill/AWA-40M-Micro-LLM-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tampakwill/AWA-40M-Micro-LLM-GGUF:F32
# Run inference directly in the terminal:
llama cli -hf tampakwill/AWA-40M-Micro-LLM-GGUF:F32

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tampakwill/AWA-40M-Micro-LLM-GGUF:F32
# Run inference directly in the terminal:
llama cli -hf tampakwill/AWA-40M-Micro-LLM-GGUF:F32

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf tampakwill/AWA-40M-Micro-LLM-GGUF:F32
# Run inference directly in the terminal:
./llama-cli -hf tampakwill/AWA-40M-Micro-LLM-GGUF:F32

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf tampakwill/AWA-40M-Micro-LLM-GGUF:F32
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tampakwill/AWA-40M-Micro-LLM-GGUF:F32

Use Docker

docker model run hf.co/tampakwill/AWA-40M-Micro-LLM-GGUF:F32

LM Studio
Jan
Ollama
How to use tampakwill/AWA-40M-Micro-LLM-GGUF with Ollama:
```
ollama run hf.co/tampakwill/AWA-40M-Micro-LLM-GGUF:F32
```

Unsloth Studio

How to use tampakwill/AWA-40M-Micro-LLM-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tampakwill/AWA-40M-Micro-LLM-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tampakwill/AWA-40M-Micro-LLM-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tampakwill/AWA-40M-Micro-LLM-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use tampakwill/AWA-40M-Micro-LLM-GGUF with Docker Model Runner:
```
docker model run hf.co/tampakwill/AWA-40M-Micro-LLM-GGUF:F32
```

Lemonade

How to use tampakwill/AWA-40M-Micro-LLM-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tampakwill/AWA-40M-Micro-LLM-GGUF:F32

Run and chat with the model

lemonade run user.AWA-40M-Micro-LLM-GGUF-F32

List all available models

lemonade list

🚀 AWA-40M (Ahmad Wildan Ardiansyah) - Version 2 (Full Daging)

AWA adalah model bahasa Micro-LLM eksperimental yang merepresentasikan versi AI dari Ahmad Wildan Ardiansyah. Setelah melalui proses training yang intens, model ini sekarang telah mencapai titik kematangan di 33 Epoch.

🧠 Update Terbaru (V2):

Training Duration: 33 Epochs (Full Cycle Completed) ✅
Optimization: Improved logic for Science, Philosophy, and Nusantara culture.
Format: GGUF (FP32) for maximum compatibility.

📊 Spesifikasi Model:

Arsitektur: GPT-2 (Custom Configuration)
Parameter: ~40-42 Million
Layers: 12
Attention Heads: 8
Embedding Dim: 512
Context Length: 1024 tokens
Training Status: Phase 2 (33 Epochs) - STABLE

🇮🇩 Karakteristik Dataset:

AWA dilatih menggunakan dataset yang dikurasi langsung oleh Ahmad Wildan Ardiansyah, mencakup:

Sains & Teknologi: Relativitas, CRISPR, IT/CS, Entropi.
Ekonomi & Geopolitik: Ekonometrika, Teori Game.
Filsafat & Psikologi: Fenomenologi, Eksistensialisme, Logika Formal.
Kekayaan Nusantara: Sejarah Majapahit, Sriwijaya, dan Kearifan Lokal.

⚙️ Cara Pakai (Format GGUF):

Gunakan file AWA-40M-Daging-V2-F32.gguf di aplikasi favorit Bos:

LM Studio
GPT4All
Layla/Maid (Android/iOS)

Dibuat dengan visi dan semangat oleh Ahmad Wildan Ardiansyah! 🔥

Downloads last month: 16

GGUF

Model size

50.3M params

Architecture

gpt2

Hardware compatibility

32-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support