Instructions to use GainEnergy/ogai-reasoner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GainEnergy/ogai-reasoner with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GainEnergy/ogai-reasoner",
	filename="ogai-reasoner.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use GainEnergy/ogai-reasoner with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf GainEnergy/ogai-reasoner
# Run inference directly in the terminal:
llama-cli -hf GainEnergy/ogai-reasoner

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf GainEnergy/ogai-reasoner
# Run inference directly in the terminal:
llama-cli -hf GainEnergy/ogai-reasoner

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 GainEnergy/ogai-reasoner
# Run inference directly in the terminal:
./llama-cli -hf GainEnergy/ogai-reasoner

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 GainEnergy/ogai-reasoner
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GainEnergy/ogai-reasoner

Use Docker

docker model run hf.co/GainEnergy/ogai-reasoner

LM Studio
Jan

vLLM

How to use GainEnergy/ogai-reasoner with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/GainEnergy/ogai-reasoner

Ollama
How to use GainEnergy/ogai-reasoner with Ollama:
```
ollama run hf.co/GainEnergy/ogai-reasoner
```

Unsloth Studio new

How to use GainEnergy/ogai-reasoner 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 GainEnergy/ogai-reasoner 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 GainEnergy/ogai-reasoner to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GainEnergy/ogai-reasoner to start chatting

Docker Model Runner
How to use GainEnergy/ogai-reasoner with Docker Model Runner:
```
docker model run hf.co/GainEnergy/ogai-reasoner
```

Lemonade

How to use GainEnergy/ogai-reasoner with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GainEnergy/ogai-reasoner

Run and chat with the model

lemonade run user.ogai-reasoner-{{QUANT_TAG}}

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

OGAI Reasoner

OGAI Reasoner is an advanced engineering system for oil and gas operations, built on the DeepSeek architecture. It specializes in petroleum engineering calculations, real-time optimization, and technical analysis.

Model Details

Base Architecture: DeepSeek (Qwen2)
Parameters: 7.62B
Quantization: Q4_K_M
Size: 4.7GB
License: MIT

Key Features

Advanced petroleum engineering calculations
Real-time optimization capabilities
Comprehensive uncertainty quantification
Industry-standard compliance
Multi-domain expertise:
- Reservoir Engineering
- Well Engineering & Drilling
- Production Engineering

Capabilities

Reservoir Analysis
- PVT calculations
- Material balance
- Pressure transient analysis
- Decline curve interpretation
Well Engineering
- Trajectory optimization
- Drilling parameter optimization
- Wellbore stability analysis
- Completion design
Production Engineering
- Nodal analysis
- Artificial lift optimization
- Network optimization
- Production forecasting

Technical Specifications

Temperature: 0.7 (Balanced precision)
Top-p: 0.95 (High coherence)
Top-k: 50 (Diverse solutions)
Presence/Frequency Penalties: 0.1

Input/Output Format

Structured JSON inputs
Standardized calculation outputs
Comprehensive metadata
Industry-standard units support

Usage Examples

# Basic calculation request
{
    "calculation_type": "pvt_analysis",
    "inputs": {
        "parameters": {
            "pressure": 3000,
            "temperature": 180,
            "oil_gravity": 35
        },
        "units": "field"
    }
}

Installation

ollama pull gainenergy/ogai-reasoner:latest

Deployment Requirements

Minimum 8GB RAM
10GB storage
CUDA-compatible GPU recommended

Best Practices

Provide complete input parameters
Specify units explicitly
Include data quality metrics
Document assumptions
Validate results against standards

Support

For technical support and questions:

GitHub Issues
Documentation: docs/
Community Forum: discuss.gainenergy.ai

License

MIT License - See LICENSE file for details

Acknowledgments

DeepSeek team for the base model architecture
Our partners, Merlin ERD
SPE for industry standards and best practices
Open-source contributors

Note: This model is optimized for engineering calculations and technical analysis. While it provides recommendations, all results should be validated by qualified engineers before implementation.

Downloads last month: -

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants