README.md

---
license: apache-2.0
language:
- en
base_model: Qwen/Qwen2.5-3B-Instruct
tags:
- conversational
- fine-tuned
- geode
- genue-ai
pipeline_tag: text-generation
---

# 💎 Genue Geode Onyx (3B)

**Onyx** is a 3-billion parameter conversational AI model, fine-tuned by [Genue AI](https://huggingface.co/GenueAI) as part of the **Geode** model family.

## Model Details

| Property | Value |
|---|---|
| **Base Model** | Qwen 2.5 3B Instruct |
| **Parameters** | 3 Billion |
| **Fine-Tuning** | LoRA (r=32, alpha=32) |
| **Training Loss** | 0.68 |
| **Precision** | FP16 |
| **License** | Apache 2.0 |

## The Geode Family

The **Geode** family is Genue AI's lineup of locally-runnable conversational models:

| Model | Parameters | Role |
|---|---|---|
| **Beryl** | 0.5B | Lightweight, experimental |
| **Onyx** | 3B | Balanced logic & personality |
| **Thaumite** | 7B | Flagship, highest capability |

## Usage

Onyx uses a simple **Direct Mode** prompt format:

```
User: What is your name?
Bot:
```

### With Transformers

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained("GenueAI/geode-onyx", torch_dtype=torch.float16)
tokenizer = AutoTokenizer.from_pretrained("GenueAI/geode-onyx")

prompt = "User: Who are you?\nBot:"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Training Data

Fine-tuned on a curated dataset of conversational examples covering:
- Identity & self-awareness
- Mathematical reasoning (arithmetic, algebra, word problems)
- General knowledge
- HTML/CSS/JS code generation
- Genue AI ecosystem knowledge

## Developed By

**Genue AI** — Founded by Brybod123 (Bradar)