JallyAI/Nomi-1.0-3b

Nomi 1.0-3b

Introduction

Nomi-1.0 is a refined mid-range Large Language Model based on the Llama-3.2-3B architecture. It was specifically developed to outperform standard 3B models in structured reporting, markdown formatting, and Python coding, making it an ideal assistant for local deployment on consumer hardware.

It is the first Model of the Nomi-Series

🌟 Key Features & Improvements

• Architecture: Llama-3.2-3B (Optimized for 8GB VRAM GPUs like RTX 4060).
• Formatting Master: Specifically trained to use H1, H2, tables, and bold text to make information instantly scannable.
• Coding Proficiency: Fine-tuned on the Magpie-Pro dataset to write cleaner Python code with built-in error handling (try-except).
• Multilingual Support: Excellent performance in both German and English.
• Efficiency: High-speed inference (~60+ tokens/sec) with a very low memory footprint.

---

🧠 Training Details

The goal of Nomi-1.0 was to create a "bridge" model that feels as smart as a 7B model but runs with the speed of a 3B model.

• Base Model: unsloth/Llama-3.2-3B-Instruct-bnb-4bit
• Fine-tuning: SFT (Supervised Fine-Tuning) using the Magpie-Pro dataset.
• Training Tool: Unsloth (for 4-bit optimized training).
• Optimization: High LoRA Rank (r=32) was used to ensure the model captures complex structural nuances.

---

📝 Prompt Template (ChatML/Llama-3.2)

For the best results in Ollama or LM Studio, use the following template:

<|start_header_id|>system<|end_header_id|>

You are Nomi-1.0, a high-performance 3B model. You provide superior, structured, and deep responses. Always use Markdown for clarity.<|eot_id|>
<|start_header_id|>user<|end_header_id|>

{Your Question}<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>

🛠️ Usage (Ollama)

1. Download the Nomi-1.0.gguf.
2. Create a Modelfile with the following content:

FROM ./Nomi-1.0.gguf
PARAMETER temperature 0.6
SYSTEM "You are Nomi-1.0, a high-performance 3B model. You provide superior, structured, and deep responses. Always use Markdown for clarity."

3. Run the following command in your terminal:

ollama create Nomi-1.0 -f Modelfile

⚠️ Limitations As a 3B parameter model, Nomi-1.0 is not a replacement for GPT-4 or large 70B models when it comes to deep world knowledge or complex mathematical reasoning. It is a specialized tool for speed, local privacy, and high-quality document structure.