Spaces:
Running
title: README
emoji: 🚀
colorFrom: blue
colorTo: red
sdk: static
pinned: false
🧠 AxionLab
Research-driven AI. Fast, smart, and brutally honest.
AxionLab is an independent lab focused on efficient language models, explicit reasoning, and lean architectures that actually run in the real world.
Less marketing. More gradient descent. 📉✨
🚀 What we do
We create and train AI models with three clear obsessions:
Efficiency: small, fast, and affordable models
Reasoning: think better > speak more
Real code: no fragile demos that break outside the laptop
If it doesn't run on common hardware, we question it. If it doesn't reason, we redo it. 🧪⚙️
🧩 Model Lines
Axion Series; our core family of models
MiniText → ultra-fast, minimal cost
MiniGPT → balance between performance and lightness
DogeAI-v1.5-Coder → total focus on small programming
DogeAI-v2.0-4B-Reasoning → reasoning, logic, and step-by-step thinking
Axion1-350k-A250k → From scratch 350k parameters MoE SLM, trained on GSM8k
MiniAxion1 → Nano Reasoning Models that surpasses models with the same size!
MiniAxion1.5 (next line of thinking models)
All focused on open research and incremental learning.
🧪 AxionLab Philosophy
Models aren't magic — they're trainable systems
Bigger isn't always better
Explicit reasoning matters
Open-source accelerates science
Benchmarks are guides, not gods
AI gets better when we question assumptions, including our own. 🧠💥
📦 What you'll find here
LLM models trained from scratch or fine-tuned
Experimental checkpoints
Ongoing research
Proprietary tokenizers
🤝Collab
We collab with:
CompactAI(https://huggingface.co/CompactAI)
💻 Hardware
RTX 5090 32GB 💪😏(CompactAI)
Radeon Vega 7 8GB 🥲👍(With ZLUDA and other techniques)(AxionLab)
🌍 Vision
To build truly accessible, auditable, and intelligent AI, not just impressive loss graphs.
AxionLab isn't about hype.
It's about understanding how to think better with machines.
📫 Contact / Collaborations Pull requests, issues, and crazy ideas are welcome.