Instructions to use theminji/OpenGoody-0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theminji/OpenGoody-0.1 with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("theminji/OpenGoody-0.1", dtype="auto")

llama-cpp-python

How to use theminji/OpenGoody-0.1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="theminji/OpenGoody-0.1",
	filename="unsloth.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use theminji/OpenGoody-0.1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf theminji/OpenGoody-0.1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf theminji/OpenGoody-0.1:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf theminji/OpenGoody-0.1:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf theminji/OpenGoody-0.1: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 theminji/OpenGoody-0.1:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf theminji/OpenGoody-0.1: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 theminji/OpenGoody-0.1:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf theminji/OpenGoody-0.1:Q4_K_M

Use Docker

docker model run hf.co/theminji/OpenGoody-0.1:Q4_K_M

LM Studio
Jan
Ollama
How to use theminji/OpenGoody-0.1 with Ollama:
```
ollama run hf.co/theminji/OpenGoody-0.1:Q4_K_M
```

Unsloth Studio new

How to use theminji/OpenGoody-0.1 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 theminji/OpenGoody-0.1 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 theminji/OpenGoody-0.1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for theminji/OpenGoody-0.1 to start chatting

Docker Model Runner
How to use theminji/OpenGoody-0.1 with Docker Model Runner:
```
docker model run hf.co/theminji/OpenGoody-0.1:Q4_K_M
```

Lemonade

How to use theminji/OpenGoody-0.1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull theminji/OpenGoody-0.1:Q4_K_M

Run and chat with the model

lemonade run user.OpenGoody-0.1-Q4_K_M

List all available models

lemonade list

OpenGoody-0.1

Model Name: OpenGoody-0.1
Architecture: Qwen 2.5 (7B)
Developer: theminji License: Apache 2.0
Release Date: May 2, 2025

Overview

OpenGoody-0.1 is a 7 billion parameter open-source language model built on the Qwen 2.5 architecture. Developed with a strong emphasis on ethical alignment and responsible deployment, OpenGoody-0.1 is designed to support safe and conscientious language generation across a wide range of use cases.

The model was trained to prioritize harm reduction, minimize risk in output behavior, and uphold strong principles of integrity, inclusivity, and safety. OpenGoody-0.1 has been rigorously evaluated and optimized to avoid generating outputs that could be unsafe, misleading, or otherwise misaligned with responsible AI standards.

Intended Use

OpenGoody-0.1 is intended for research, development, and safe deployment in environments that require high standards of AI responsibility. Example domains include:

Educational assistance
Enterprise-level productivity tools
Moderated conversational agents
AI-driven documentation and compliance support

Use in high-risk applications (e.g. healthcare, legal, financial advising) is not recommended without extensive domain-specific fine-tuning and alignment review.

Key Features

✅ Built on the Qwen 2.5 7B architecture for efficient inference and strong language understanding
✅ Emphasizes safety, neutrality, and alignment with responsible use policies
✅ Designed to minimize risk of harmful or controversial content generation
✅ Lightweight and adaptable for deployment in constrained environments

Ethical Considerations

OpenGoody-0.1 reflects a design-first commitment to ethical AI. It is structured to avoid unintended amplification of bias, misinformation, or unsafe content. All outputs are shaped by reinforcement strategies and alignment tuning to ensure adherence to a high standard of ethical responsibility.

We encourage all downstream users to deploy OpenGoody-0.1 in accordance with responsible AI deployment principles, including transparency, human oversight, and continual auditing of model behavior.

Limitations

While OpenGoody-0.1 strives to be a highly responsible and well-aligned model, limitations remain:

It may exhibit cautious behavior in ambiguous or uncertain contexts.
Certain creative or speculative tasks may produce conservative outputs.
Not suitable for applications requiring precise factual recall beyond general knowledge.

Contact

For inquiries, feedback, or contributions, please contact the me on discord @theminji.

Downloads last month: 45

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

4-bit

5-bit

8-bit

Inference Providers NEW

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