Cygnis-Alpha-2-8B-v0.2

<div align="center"> <img src="https://cygnis-ai.vercel.app/favicon.ico" width="80" height="80" style="border-radius: 50%; border: 2px solid #f0f0f0; box-shadow: 0 4px 8px rgba(0,0,0,0.1); margin-bottom: 15px; object-fit: cover;"> <h1>Cygnis-Alpha-2 8B v0.2</h1> <p><i>The Sovereign Reasoning Engine by Simonc-44</i></p> </div> <div style="overflow-x: auto; scrollbar-width: none; -ms-overflow-style: none; -webkit-overflow-scrolling: touch; padding: 10px 0;"> <style> div::-webkit-scrollbar { display: none; } </style> <table align="center" style="border-collapse: collapse; border: none; margin: 0 auto;"> <tr style="border: none;"> <td style="border: none; padding: 0 5px;"> <a href="https://huggingface.co/Simonc-44/Cygnis-Alpha-2-7B-v0.2/blob/main/Cygnis_Alpha_2.7B_Technical_Report.pdf" style="text-decoration: none;"> <div style="background: #000; color: #fff; padding: 6px 14px; border-radius: 50px; font-weight: 600; font-family: sans-serif; font-size: 11px; border: 1px solid #333; display: flex; align-items: center; white-space: nowrap;"> <svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="white" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" style="margin-right: 8px;"><path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8z"></path><polyline points="14 2 14 8 20 8"></polyline><line x1="16" y1="13" x2="8" y2="13"></line><line x1="16" y1="17" x2="8" y2="17"></line><polyline points="10 9 9 9 8 9"></polyline></svg> TECHNICAL REPORT </div> </a> </td> <td style="border: none; padding: 0 5px;"> <a href="https://huggingface.co/Simonc-44/Cygnis-Alpha-2-8B-v0.2-GGUF" style="text-decoration: none;"> <div style="background: #7b1fa2; color: #fff; padding: 6px 14px; border-radius: 50px; font-weight: 600; font-family: sans-serif; font-size: 11px; border: 1px solid #4a148c; display: flex; align-items: center; white-space: nowrap;"> <svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="white" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" style="margin-right: 8px;"><path d="M21 16V8a2 2 0 0 0-1-1.73l-7-4a2 2 0 0 0-2 0l-7 4A2 2 0 0 0 3 8v8a2 2 0 0 0 1 1.73l7 4a2 2 0 0 0 2 0l7-4A2 2 0 0 0 21 16z"></path><polyline points="3.27 6.96 12 12.01 20.73 6.96"></polyline><line x1="12" y1="22.08" x2="12" y2="12"></line></svg> GGUF VERSIONS </div> </a> </td> <td style="border: none; padding: 0 5px;"> <a href="https://huggingface.co/spaces/Simonc-44/Cygnis-Alpha-2-Chat" style="text-decoration: none;"> <div style="background: #fff; color: #000; padding: 6px 14px; border-radius: 50px; font-weight: 600; font-family: sans-serif; font-size: 11px; border: 1px solid #ddd; display: flex; align-items: center; white-space: nowrap;"> <img src="https://huggingface.co/front/assets/huggingface_logo-noborder.svg" width="14" style="margin-right: 8px;"> LIVE DEMO </div> </a> </td> <td style="border: none; padding: 0 5px;"> <a href="https://www.apache.org/licenses/LICENSE-2.0" style="text-decoration: none;"> <div style="background: #1a1a1a; color: #fff; padding: 6px 14px; border-radius: 50px; font-weight: 600; font-family: sans-serif; font-size: 11px; border: 1px solid #333; display: flex; align-items: center; white-space: nowrap;"> <svg width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="#888" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" style="margin-right: 8px;"><path d="M12 22s8-4 8-10V5l-8-3-8 3v7c0 6 8 10 8 10z"></path></svg> APACHE 2.0 </div> </a> </td> </tr> </table> </div>

Model Card for Cygnis-Alpha-2 8B v0.2

Cygnis-Alpha-2 8B v0.2 is the full, independent version of the Cygnis Alpha model. Unlike v0.1, which was a LoRA adapter, this release contains merged weights (Full Weights), allowing it to operate as a standalone model without requiring a third-party base model.

Optimized by Simonc-44, this model implements a systematic reasoning process (Chain-of-Thought) before generating final outputs, ensuring logical consistency and enhanced performance in both French and English.

Model Architecture

Cygnis-Alpha-2 8B v0.2 is based on a Llama 3.1 architecture, featuring:

• Merged Weights: Independent execution without base model dependency.
• Reasoning Capabilities: Integrated CoT processing to reduce hallucinations.
• Native ChatML Support: Optimized for structured role-based interactions.

Performance Benchmarks

Comparaison estimée par rapport aux modèles de taille similaire (3B Parameters)

<p style="font-size: 10px; color: gray;">* Scores en cours de validation sur l'Open LLM Leaderboard.</p>

Instruction Format

Cygnis-Alpha-2 8B v0.2 utilizes the ChatML format. For optimal results, use the following structure:

| **MMLU** | **52.4*** | 49.3 | 42.1 |
<|im_start|>system
You are Cygnis Alpha 2, a sovereign AI created by Simonc-44. You are concise, clear, and helpful.<|im_end|>
<|im_start|>user
[Your question here]<|im_end|>
<|im_start|>assistant
<|im_thought|>
[Model's internal reasoning...]
<|im_end|>
[Final response]

Quickstart

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Simonc-44/Cygnis-Alpha-2-8B-v0.2"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

messages = [{"role": "user", "content": "Explain the concept of digital sovereignty."}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to("cuda")
outputs = model.generate(inputs, max_new_tokens=500)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

GGUF Versions

The optimized GGUF versions are now fully available, ranging from Q2_K to Q8_0, including the full FP16 weights.

These models have been specifically quantized using llama.cpp to ensure that the Reasoning Engine (<|im_thought|>) maintains its full logic integrity and chain-of-thought capabilities, even at lower bitrates.

Available Quantizations

👉 Access the GGUF Repository here: Simonc-44/Cygnis-Alpha-2-7B-v0.2-GGUF

Notice

Cygnis-Alpha-2 8B v0.2 is a fine-tuned model and does not have built-in moderation mechanisms. Users should be aware that the model may reflect biases present in the training data or base architecture.

The Cygnis Project Team

Developed and refined by Simonc-44.