Instructions to use DestinBir/buzy-ai-gemma4-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DestinBir/buzy-ai-gemma4-lora with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="DestinBir/buzy-ai-gemma4-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("DestinBir/buzy-ai-gemma4-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DestinBir/buzy-ai-gemma4-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DestinBir/buzy-ai-gemma4-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DestinBir/buzy-ai-gemma4-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DestinBir/buzy-ai-gemma4-lora

SGLang

How to use DestinBir/buzy-ai-gemma4-lora with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "DestinBir/buzy-ai-gemma4-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DestinBir/buzy-ai-gemma4-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "DestinBir/buzy-ai-gemma4-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DestinBir/buzy-ai-gemma4-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use DestinBir/buzy-ai-gemma4-lora 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 DestinBir/buzy-ai-gemma4-lora 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 DestinBir/buzy-ai-gemma4-lora to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for DestinBir/buzy-ai-gemma4-lora to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="DestinBir/buzy-ai-gemma4-lora",
    max_seq_length=2048,
)

Docker Model Runner
How to use DestinBir/buzy-ai-gemma4-lora with Docker Model Runner:
```
docker model run hf.co/DestinBir/buzy-ai-gemma4-lora
```

Buzy AI – Business Reasoning LoRA for Gemma 4

Buzy AI is a LoRA adapter built on Gemma 4 that specializes the model for explainable business reasoning over enterprise documents.

Rather than acting as a generic chatbot, Buzy AI transforms business information into structured, evidence-based recommendations to support decision-making.

Model Details

Developed by: Destin Biringanine
Entreprise: Code, Growth Alive
Base model: unsloth/gemma-4-E2B-it-unsloth-bnb-4bit
Fine-tuning: LoRA (PEFT)
Framework: Unsloth
License: Apache-2.0

Intended Use

This model is designed for enterprise decision-support tasks, including:

Contract analysis
Invoice understanding
Procurement intelligence
Supplier risk assessment
Financial document analysis
Business reporting
Explainable recommendations

The model follows a structured reasoning process consisting of:

Evidence
Reasoning
Confidence
Business Impact
Recommended Actions

Training

The adapter was fine-tuned using Unsloth on a structured business reasoning dataset.

The objective was not to teach new business knowledge, but to improve the model's ability to produce consistent, transparent, and explainable business reasoning.

Example

Input

Supplier A has delayed deliveries for three consecutive months.
The defect rate increased by 18%.
The contract expires next month.
Should the contract be renewed?

Output

{
  "decision": "Do not renew without corrective actions.",
  "evidence": [
    "Three consecutive delivery delays",
    "18% increase in defect rate"
  ],
  "reasoning": "Operational performance has consistently deteriorated, increasing supply-chain risk.",
  "confidence": 0.95,
  "business_impact": "High operational risk",
  "recommended_actions": [
    "Request a corrective action plan",
    "Evaluate alternative suppliers",
    "Conduct a supplier performance review"
  ]
}

Limitations

This model is intended for research and demonstration purposes.

It should be used as a decision-support assistant rather than an autonomous decision-maker and performs best when combined with an external knowledge base or retrieval system.

Acknowledgements

This project was developed for the Build with Google Gemma Hackathon using:

Google Gemma
Unsloth
Hugging Face Transformers
PEFT
PyTorch

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for DestinBir/buzy-ai-gemma4-lora

Base model

google/gemma-4-E2B

Finetuned

google/gemma-4-E2B-it

Quantized

unsloth/gemma-4-E2B-it-unsloth-bnb-4bit

Adapter

(10)

this model