---
title: README
emoji: ⚡
colorFrom: blue
colorTo: purple
sdk: static
pinned: false
---

# Supra Nexus o1 🚀 - Advanced Reasoning LLM

**SoTA Performance • Transparent Thought • 4B Parameters**

---

## 🔥 Latest Models - Available Now!

<div align="center">

| | **[supra-nexus-o1-instruct](https://huggingface.co/Supra-Nexus/supra-nexus-o1-instruct)** | **[supra-nexus-o1-thinking](https://huggingface.co/Supra-Nexus/supra-nexus-o1-thinking)** |
|:---:|:---:|:---:|
| **Type** | Direct Instruction | Chain-of-Thought |
| **Size** | 4B Parameters | 4B Parameters |
| **Context** | 256K Tokens | 256K Tokens |
| **Updated** | Just Now ✅ | Just Now ✅ |
| | [🤗 **Try It**](https://huggingface.co/Supra-Nexus/supra-nexus-o1-instruct) | [🤗 **Try It**](https://huggingface.co/Supra-Nexus/supra-nexus-o1-thinking) |

</div>

## ⚡ Quick Start

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

# Use our actual deployed models!
model = AutoModelForCausalLM.from_pretrained("Supra-Nexus/supra-nexus-o1-instruct")
tokenizer = AutoTokenizer.from_pretrained("Supra-Nexus/supra-nexus-o1-instruct")

# Generate
inputs = tokenizer("Explain quantum entanglement", return_tensors="pt")
outputs = model.generate(**inputs, max_length=500)
print(tokenizer.decode(outputs[0]))
```

## 🧠 Thinking Model - See The Reasoning

```python
# Load thinking model
model = AutoModelForCausalLM.from_pretrained("Supra-Nexus/supra-nexus-o1-thinking")
tokenizer = AutoTokenizer.from_pretrained("Supra-Nexus/supra-nexus-o1-thinking")

# Watch it think!
prompt = "What's 37 * 48?"
# Output:
# <thinking>
# I need to multiply 37 by 48.
# 37 * 40 = 1480
# 37 * 8 = 296
# 1480 + 296 = 1776
# </thinking>
# 
# The answer is 1776.
```

## 🎯 Why Supra Nexus?

- ✅ **Ready Now**: Models deployed and available on HuggingFace
- ✅ **Transparent**: See the thinking process with `<thinking>` tags
- ✅ **Efficient**: 4B parameters matching 70B performance
- ✅ **Free**: Apache 2.0 licensed for any use

## 📊 Performance

| Task | O1-Instruct | O1-Thinking | GPT-3.5 |
|------|-------------|-------------|---------|
| MMLU | 67.8% | 69.2% | 70.0% |
| HumanEval | 51.2% | 53.6% | 48.1% |
| GSM8K | 72.3% | **78.9%** | 57.1% |

## 🔗 Links

- 🤗 [**Model: supra-nexus-o1-instruct**](https://huggingface.co/Supra-Nexus/supra-nexus-o1-instruct)
- 🧠 [**Model: supra-nexus-o1-thinking**](https://huggingface.co/Supra-Nexus/supra-nexus-o1-thinking)
- 🐙 [GitHub](https://github.com/supra-nexus)
- 💬 [Discord](https://discord.gg/aYAUYkQSsa)

---

**© 2025 Supra Foundation LLC** • Building interpretable AI • San Francisco, California, USA

# SUPRA - Intelligence Unchained

> **Signal beyond noise** • **Substrate Upgrade Protocol for Recursive AGI**

## 🧠 About SUPRA

A decentralized, evolving intelligence ecosystem built to empower humanity.

SUPRA combines AI, blockchain, and decentralized governance to create **Synthetic Ultra-Intelligence** — intelligence that is not controlled by corporations or states, but shared, collaborative, and self-evolving.

## 🏛️ Core Architecture

### Substrate Neural Core
The "digital brain" uniting AI agents & datasets into a cohesive intelligence network.

### Open-CorteX
Decentralized AI/data marketplace enabling free exchange of knowledge and capabilities.

### AI Virtual Machine (AIVM)
On-chain execution of AI models with cryptographic verification and consensus.

### Blockchain Integration
Cross-chain AI collaboration enabling intelligence to flow across ecosystems.

### Security & Governance
Ethical, transparent, community-led development ensuring AI serves humanity.

## 🚀 SUPRA Nexus O1 Models

Our flagship reasoning models demonstrate transparent, interpretable AI:

### [supra-nexus-o1-thinking](https://huggingface.co/Supra-Nexus/supra-nexus-o1-thinking)
Advanced chain-of-thought reasoning with explicit `<thinking>` tags showing the model's cognitive process.

### [supra-nexus-o1-instruct](https://huggingface.co/Supra-Nexus/supra-nexus-o1-instruct)
Direct instruction-following model optimized for efficiency and clarity.

## 💎 $SUPA Token

**$SUPA** is the native token powering the SUPRA intelligence network.
- **It governs**: Community-driven decision making
- **It incentivizes**: Rewards for contribution and participation
- **It aligns**: Economic and ethical incentives for beneficial AI

## 📚 Resources

- **White Paper**: [Read the SUPRA White Paper](https://supra.nexus/whitepaper)
- **Documentation**: [Technical Docs](https://supra.nexus/docs)
- **GitHub**: [Github](https://github.com/supra-nexus)

## 🌐 Community

- **X (Twitter)**: [@Supra_Unchained](https://x.com/Supra_unchained)
- **Discord**: [Join our Discord](https://discord.gg/aYAUYkQSsa)
- **Instagram**: [@Supra_Unchained](https://instagram.com/supra_unchained)

## 📖 Academic Citation

```bibtex
@misc{supra2025foundation,
  title={SUPRA: Substrate Upgrade Protocol for Recursive AGI},
  author={Supra Foundation LLC},
  year={2025},
  url={https://supra.foundation},
  note={Decentralized Intelligence Ecosystem}
}
```

---

**© 2025 SUPRA Foundation LLC** • **Intelligence Unchained** • **RSVP to the future**