Spaces:
Configuration error
Configuration error
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
-
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
# Welcome to ThingsAI! 🤗
|
| 3 |
+
|
| 4 |
+
**Building efficient, bilingual AI models that run anywhere.** 🇮🇹 🇬🇧
|
| 5 |
+
|
| 6 |
---
|
| 7 |
+
|
| 8 |
+
## 🤖 Our Models
|
| 9 |
+
|
| 10 |
+
### [Quark-135M](https://huggingface.co/ThingAI/Quark-135m-Bilingual)
|
| 11 |
+
A lightweight bilingual (Italian + English) language model with **135M parameters**. Features GQA, SwiGLU, RMSNorm, and RoPE. Trained on 50B+ tokens of curated Italian and English data.
|
| 12 |
+
|
| 13 |
+
### Quark-270M *(training now)*
|
| 14 |
+
Our most powerful small model — **270M parameters** with 32 layers, 768 hidden dimensions, and 65K vocabulary. Currently in active training on 10B+ tokens with planned scaling to 135B tokens.
|
| 15 |
+
|
| 16 |
+
### [Quark-Mod](https://huggingface.co/ThingAI/Quark-Mod)
|
| 17 |
+
A multi-label moderation model covering **9 categories** for safe AI deployment: toxic, severe_toxic, obscene, threat, insult, identity_hate, cyberbullying, hate_speech, offensive.
|
| 18 |
+
|
| 19 |
---
|
| 20 |
|
| 21 |
+
## 🎯 What We Focus On
|
| 22 |
+
|
| 23 |
+
- ⚡ **Small, efficient architectures** — GQA, weight tying, deep-thin design
|
| 24 |
+
- 🌍 **Bilingual training** — Italian + English from scratch
|
| 25 |
+
- 🔓 **Open-source everything** — weights, code, datasets
|
| 26 |
+
- 💻 **Real-world deployment** — runs on consumer hardware
|
| 27 |
+
|
| 28 |
+
---
|
| 29 |
+
|
| 30 |
+
## 📂 Resources
|
| 31 |
+
|
| 32 |
+
| | |
|
| 33 |
+
|---|---|
|
| 34 |
+
| 📚 [Quark-135M-Bilingual](https://huggingface.co/ThingAI/Quark-135m-Bilingual) | Our flagship bilingual model |
|
| 35 |
+
| 🛡️ [Quark-Moderation-Multi](https://huggingface.co/ThingsAI/Quark-Mod) | Multi-label content moderation |
|
| 36 |
+
| 📝 [HuggingFace Community](https://huggingface.co/ThingsAI) | All our models and datasets |
|
| 37 |
+
| 💻 [GitHub](https://github.com/overcastlab) | Code, scripts, and tools |
|
| 38 |
+
|
| 39 |
+
---
|
| 40 |
|
| 41 |
+
<p align="center">
|
| 42 |
+
<sub>Made with ❤️ by ThingsAI · <a href="https://things-ai.org">Website</a> · <a href="https://github.com/overcastlab">GitHub</a></sub>
|
| 43 |
+
</p>
|