πŸ’Ž Genue Geode Onyx (3B)

Onyx is a 3-billion parameter conversational AI model, fine-tuned by Genue AI 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

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 β€” Founded by Brybod123 (Bradar)

Downloads last month
236
Safetensors
Model size
3B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for GenueAI/geode-onyx

Base model

Qwen/Qwen2.5-3B
Finetuned
(1166)
this model
Quantizations
1 model