Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Atom 27B
|
| 2 |
|
| 3 |
-
**A collaboration-first AI assistant designed to be your thinking partner, not just an information source.**
|
| 4 |
|
| 5 |
-
Atom 27B is the fourth model in the Project Atom series, which progressively scales the Atom persona from 4B to 400B+ parameters. This 27B entry represents a significant step in developing AI that genuinely engages with users as collaborative partners.
|
| 6 |
|
| 7 |
## Model Overview
|
| 8 |
|
|
@@ -140,4 +183,4 @@ Please refer to the base Gemma 3 license terms.
|
|
| 140 |
|
| 141 |
---
|
| 142 |
|
| 143 |
-
*Built by Vanta Research*
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gemma
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
base_model:
|
| 6 |
+
- google/gemma-3-27b-it
|
| 7 |
+
tags:
|
| 8 |
+
- conversational-ai
|
| 9 |
+
- vanta-research
|
| 10 |
+
- collaborative-ai
|
| 11 |
+
- chat
|
| 12 |
+
- chatbot
|
| 13 |
+
- roleplay
|
| 14 |
+
- reasoning
|
| 15 |
+
- friendly
|
| 16 |
+
- google
|
| 17 |
+
- gemma3
|
| 18 |
+
- gemma
|
| 19 |
+
- project-atom
|
| 20 |
+
- LLM
|
| 21 |
+
- language-model
|
| 22 |
+
- text-generation
|
| 23 |
+
- text-generation-inference
|
| 24 |
+
- apache
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<div align="center">
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
<h1>VANTA Research</h1>
|
| 32 |
+
|
| 33 |
+
<p><strong>Independent AI research lab building safe, resilient language models optimized for human-AI collaboration</strong></p>
|
| 34 |
+
|
| 35 |
+
<p>
|
| 36 |
+
<a href="https://vantaresearch.xyz"><img src="https://img.shields.io/badge/Website-vantaresearch.xyz-black" alt="Website"/></a>
|
| 37 |
+
<a href="https://merch.vantaresearch.xyz"><img src="https://img.shields.io/badge/Merch-merch.vantaresearch.xyz-sage" alt="Merch"/></a>
|
| 38 |
+
<a href="https://x.com/vanta_research"><img src="https://img.shields.io/badge/@vanta_research-1DA1F2?logo=x" alt="X"/></a>
|
| 39 |
+
<a href="https://github.com/vanta-research"><img src="https://img.shields.io/badge/GitHub-vanta--research-181717?logo=github" alt="GitHub"/></a>
|
| 40 |
+
</p>
|
| 41 |
+
</div>
|
| 42 |
+
|
| 43 |
+
---
|
| 44 |
# Atom 27B
|
| 45 |
|
| 46 |
+
**A friendly, collaboration-first AI assistant designed to be your thinking partner, not just an information source.**
|
| 47 |
|
| 48 |
+
Atom 27B is the fourth model in the Project Atom series, which progressively scales the Atom persona from 4B to 400B+ parameters. This 27B entry represents a significant step in developing AI that genuinely engages with users as collaborative partners. This model is the **largest** from VANTA Research to-date, and remains committed to our pursuit of frontier human-AI collaboration.
|
| 49 |
|
| 50 |
## Model Overview
|
| 51 |
|
|
|
|
| 183 |
|
| 184 |
---
|
| 185 |
|
| 186 |
+
*Built by Vanta Research*
|