From 2967a8ae4e76b643d24986e51446c60361167c06 Mon Sep 17 00:00:00 2001
From: Loubna Ben Allal <44069155+loubnabnl@users.noreply.github.com>
Date: Tue, 8 Jul 2025 17:08:25 +0200
Subject: [PATCH] Update README.md

---
 README.md | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 84ff139..ad8fb87 100644
--- a/README.md
+++ b/README.md
@@ -3,8 +3,7 @@
 Welcome to Smol Models, a family of efficient and lightweight AI models from Hugging Face. Our mission is to create powerful yet compact models, for text and vision, that can run effectively on-device while maintaining strong performance.
 
 **News 📰**
-- **Introducing [FineMath](https://huggingface.co/datasets/HuggingFaceTB/finemath), the best public math pretraining dataset 🚀**
-- Added continual pretraining code for Llama 3.2 3B on FineMath & FineWeb-Edu with `nanotron`
+- **Releasing [SmolLM3](https://huggingface.co/HuggingFaceTB/SmolLM3-3B), new smol, multilingual and long-context reasoner 🚀**
 
 ## 💬 SmolLM2 (Language Model)
 [SmolLM2](https://huggingface.co/collections/HuggingFaceTB/smollm2-6723884218bcda64b34d7db9) is our family of compact language models available in three sizes:
@@ -82,4 +81,4 @@ messages = [
 ### Datasets
 - [SmolTalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) - Our instruction-tuning dataset
 - [FineMath](https://huggingface.co/datasets/HuggingFaceTB/finemath) - Mathematics pretraining dataset
-- [FineWeb-Edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu) - Educational content pretraining dataset
\ No newline at end of file
+- [FineWeb-Edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu) - Educational content pretraining dataset