Instructions to use OmnipotentFool/Aurvion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OmnipotentFool/Aurvion with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="OmnipotentFool/Aurvion",
	filename="craft_output\CRAFT_Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use OmnipotentFool/Aurvion 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 OmnipotentFool/Aurvion:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf OmnipotentFool/Aurvion:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf OmnipotentFool/Aurvion:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf OmnipotentFool/Aurvion:Q4_K_M

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 OmnipotentFool/Aurvion:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf OmnipotentFool/Aurvion:Q4_K_M

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 OmnipotentFool/Aurvion:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf OmnipotentFool/Aurvion:Q4_K_M

Use Docker

docker model run hf.co/OmnipotentFool/Aurvion:Q4_K_M

LM Studio
Jan

vLLM

How to use OmnipotentFool/Aurvion with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OmnipotentFool/Aurvion"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OmnipotentFool/Aurvion",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OmnipotentFool/Aurvion:Q4_K_M

Ollama
How to use OmnipotentFool/Aurvion with Ollama:
```
ollama run hf.co/OmnipotentFool/Aurvion:Q4_K_M
```

Unsloth Studio

How to use OmnipotentFool/Aurvion 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 OmnipotentFool/Aurvion 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 OmnipotentFool/Aurvion to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for OmnipotentFool/Aurvion to start chatting

Atomic Chat new
Docker Model Runner
How to use OmnipotentFool/Aurvion with Docker Model Runner:
```
docker model run hf.co/OmnipotentFool/Aurvion:Q4_K_M
```

Lemonade

How to use OmnipotentFool/Aurvion with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull OmnipotentFool/Aurvion:Q4_K_M

Run and chat with the model

lemonade run user.Aurvion-Q4_K_M

List all available models

lemonade list

CRAFT-Phi3-Mini

CRAFT (Curriculum-guided Reinforced Adaptive Fine-Tuning) is a reasoning-enhanced version of Phi-3-Mini, trained to address three specific failure modes of reinforcement learning applied to small language models: training instability, unreliable reward signals, and outcome-blind learning.

Built for Samsung EnnovateX 2026, Problem Statement 06.

Model Details

Base model: microsoft/Phi-3-mini-4k-instruct
Training method: SFT warmup + GRPO with three custom components
Format: GGUF, 4-bit quantized (Q4_K_M)
Size: ~2.2GB
License: Apache 2.0

How CRAFT Was Trained

Capability Probe — measured base model difficulty per-question before training
SFT Warmup — QLoRA fine-tuning on GSM8K + AQuA-RAT
CRAFT RL Loop — GRPO with:
- Deterministic execution verifier (Python-based math reward, NLI-based logic reward)
- Contrastive step-level preference learning (self-supervised, no human labels)
- Live adaptive curriculum (dynamic difficulty + KL control)
Deployment — quantized to 4-bit GGUF for on-device inference

Benchmark Results

Benchmark	Baseline (Phi-3-Mini)	CRAFT	Improvement
GSM8K	48%	62%	69.05%
StrategyQA	42%	71%	70.27%
MMLU	37%	63%	29.17%

Evaluated using lm-evaluation-harness.

Usage

pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama(model_path="CRAFT_Q4_K_M.gguf", n_ctx=2048)
output = llm("Solve step by step: What is 15% of 240?", max_tokens=256)
print(output["choices"][0]["text"])

Intended Use

On-device reasoning for resource-constrained environments — laptops, edge devices, and offline applications requiring multi-step mathematical and logical reasoning without cloud dependency.

Limitations

[Be honest here — e.g., "Performance gains are most pronounced on arithmetic reasoning tasks; gains on broader knowledge benchmarks (MMLU) are comparatively smaller, reflecting the training data composition."]

Citation / Acknowledgment

Built for Samsung EnnovateX 2026 Hackathon, Problem Statement 06. Base model: Microsoft Phi-3-Mini.

Repository

Full source code, training pipeline, and documentation: GitHub link

Downloads last month: 14

GGUF

Model size

4B params

Architecture

phi3

Hardware compatibility

4-bit

Model tree for OmnipotentFool/Aurvion

Base model

microsoft/Phi-3-mini-4k-instruct

Quantized

(172)

this model

OmnipotentFool
/

Aurvion