README overhaul

README.md

@@ -7,34 +7,91 @@ sdk: static
 pinned: false
 ---
 
-![axiomic banner](AxiomicBanner.png)
+<div align="center">
 
-Axiomic Labs is an independent, Australian based, AI research lab. Our work explores how small models can achieve stronger capabilities through better training data, compact architectures, and targeted benchmarks.
+![Axiomic Labs Banner](AxiomicBanner.png)
 
-## Latest releases
+
+**Axiomic Labs is an independent, Australian based, AI research lab. Our work explores how small models can achieve stronger capabilities through better training data, compact architectures, and targeted benchmarks.**
+
+[![Website](https://img.shields.io/badge/Website-axiomiclabs.com-111827?style=for-the-badge)](https://www.axiomiclabs.com)
+[![Hugging Face](https://img.shields.io/badge/🤗_Hugging_Face-AxiomicLabs-FFD21E?style=for-the-badge&labelColor=111827)](https://huggingface.co/AxiomicLabs)
+[![Leaderboard](https://img.shields.io/badge/🤗_Leaderboard-Open_SLM_Leaderboard-FFD21E?style=for-the-badge&labelColor=111827)](https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard)
+</div>
+
+---
+
+## Latest Releases
 
 ### Models
-- **[GPT-S2-5M](https://huggingface.co/AxiomicLabs/GPT-S2-5M)** - The latest and most capable member of GPT-S family, featuring our latest T-X4 architecture and achieving **#1** on the open SLM leaderboard sub 10m category.
-- **[GPT-S-1.4M](https://huggingface.co/AxiomicLabs/GPT-S-1.4M)** - The tiniest member of our small model GPT-S family, featuring our T-X3 architecture.
-- **[GPT-X2-125M](https://huggingface.co/AxiomicLabs/GPT-X2-125M)** - Our flagship language model featuring our second-generation T-X2 architecture and achieving near state-of-the-art performance at the 125M scale.
+
+| Model | Description |
+|---|---|
+| **[GPT-S2-5M](https://huggingface.co/AxiomicLabs/GPT-S2-5M)** | Most capable member of the GPT-S family — new **T-X4** architecture, **#1** on the Open SLM Leaderboard (sub-10M category) |
+| **[GPT-S-1.4M](https://huggingface.co/AxiomicLabs/GPT-S-1.4M)** | Our tiniest small model, built on the **T-X3** architecture |
+| **[GPT-X2-125M](https://huggingface.co/AxiomicLabs/GPT-X2-125M)** | Flagship model featuring second-gen **T-X2** architecture — near state-of-the-art at 125M scale |
 
 ### Benchmarks
 
-- **[ArithMark-3.0](https://huggingface.co/datasets/AxiomicLabs/ArithMark-3.0)** - The 3rd iteration of our arithmetic benchmark, 1000 word problems, 17 categories, used in the [Open SLM Leaderboard](https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard).
+| Benchmark | Description |
+|---|---|
+| **[ArithMark-3.0](https://huggingface.co/datasets/AxiomicLabs/ArithMark-3.0)** | 3rd-gen arithmetic benchmark — 1,000 word problems across 17 categories. Powers the [Open SLM Leaderboard](https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard) |
 
 ### Datasets
 
-- **[NPset-2-Python-Edu](https://huggingface.co/datasets/AxiomicLabs/NPset-2-Python-Edu)** - Our latest Natural language code dataset, converted from stack-edu (python split), parsed using the all new NPset-2 spec
+| Dataset | Description |
+|---|---|
+| **[NPset-2-Python-Edu](https://huggingface.co/datasets/AxiomicLabs/NPset-2-Python-Edu)** | Natural-language code dataset, converted from stack-edu (Python split) using the new **NPset-2** spec |
 
-### Other
+### Tools
 
-- **[Open SLM Leaderboard](https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard)** - A leaderboard for Small language models (<150m parameters) scored on 5 hand picked benchmarks. See how our models stack up against our competitors.
+| Tool | Description |
+|---|---|
+| **[Open SLM Leaderboard](https://huggingface.co/spaces/AxiomicLabs/Open_SLM_Leaderboard)** | Ranks small language models (<150M params) across 5 hand-picked benchmarks |
+
+---
+
+## Team
+
+<div align="center">
+<table>
+  <tr>
+    <td align="center" width="140">
+      <a href="https://huggingface.co/Datdanboi25" target="_blank">
+        <img src="https://cdn-avatars.huggingface.co/v1/production/uploads/67b413df70aa5c739bda9e7a/YPcjlXG5TIwuxCbVzSn-F.jpeg" width="80" height="80" style="border-radius: 50%; object-fit: cover;"/>
+        <br/><br/>
+        <b>Datdanboi25</b>
+      </a>
+    </td>
+    <td align="center" width="140">
+      <a href="https://huggingface.co/Mmorgan-ML" target="_blank">
+        <img src="https://huggingface.co/avatars/08dbfa2c62ae6b44bf78de8c6099b022.svg" width="80" height="80" style="border-radius: 50%; object-fit: cover;"/>
+        <br/><br/>
+        <b>Mmorgan-ML</b>
+      </a>
+    </td>
+    <td align="center" width="140">
+      <a href="https://huggingface.co/Datdanboi25" target="_blank">
+        <img src="https://cdn-avatars.huggingface.co/v1/production/uploads/65d3d84d457647eb547ed73b/4yhQhLjJfsMzfdsfQwmwr.png" width="80" height="80" style="border-radius: 50%; object-fit: cover;"/>
+        <br/><br/>
+        <b>Datdanboi25</b>
+      </a>
+    </td>
+  </tr>
+</table>
+</div>
+
+<div align="center">
+
+**We're always looking for talented, knowledgeable collaborators.**
+To apply, open a discussion on this README.
+
+</div>
+
+---
 
-## Members
-- **[Datdanboi25](https://huggingface.co/Datdanboi25)**
-- **[Mmorgan-ML](https://huggingface.co/Mmorgan-ML)**
-- **[Enderchef](https://huggingface.co/Enderchef)**
+<div align="center">
 
-We are always looking for more technical and knowledgable members, to apply please open a discussion on this README.
+**[www.axiomiclabs.com](https://www.axiomiclabs.com)**
 
-Visit our website: https://www.axiomiclabs.com
+</div>