Improve model card: Add pipeline tag, enrich tags, update license, and add top-level links

README.md

@@ -1,5 +1,5 @@
 ---
-library_name: transformers
+base_model: tiiuae/Falcon-H1-7B-Base
 language:
 - ar
 - cs
@@ -19,18 +19,25 @@ language:
 - sv
 - ur
 - zh
+library_name: transformers
+license: apache-2.0
 tags:
 - falcon-h1
-license: other
-license_name: falcon-llm-license
-license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
-base_model: tiiuae/Falcon-H1-7B-Base
+- multilingual
+- code-generation
+- math
+- reasoning
+- instruction-tuned
+- science
 inference: true
+pipeline_tag: text-generation
 ---
 
+[\ud83d\udcc4 Paper](https://huggingface.co/papers/2507.22448) | [\ud83d\udcbb Code](https://github.com/tiiuae/Falcon-H1) | [\ud83c\udfe0 Project Page](https://tiiuae.github.io/Falcon-H1/)
+
 <img src="https://huggingface.co/datasets/tiiuae/documentation-images/resolve/main/falcon_mamba/falcon-h1-logo.png" alt="drawing" width="800"/>
 
-#  Table of Contents
+# Table of Contents
 
 0. [TL;DR](#TL;DR)
 1. [Model Details](#model-details)
@@ -40,6 +47,7 @@ inference: true
 5. [Citation](#citation)
 
 # TL;DR
+Falcon-H1 is a new family of hybrid-head Large Language Models (LLMs) ranging from 0.5B to 34B parameters. They combine Transformer-based attention with State Space Models (SSMs) for superior long-context memory and computational efficiency. These models achieve state-of-the-art performance across reasoning, mathematics, multilingual tasks, instruction following, and scientific knowledge, outperforming larger models in efficiency and performance. They support up to 256K context tokens and 18 languages, and are released under a permissive open-source license.
 
 # Model Details
 
@@ -49,7 +57,7 @@ inference: true
 - **Model type:** Causal decoder-only
 - **Architecture:** Hybrid Transformers + Mamba architecture
 - **Language(s) (NLP):** English, Multilingual
-- **License:** Falcon-LLM License
+- **License:** Apache 2.0
 
 # Training details
 
@@ -147,6 +155,7 @@ You can check more in detail on our [our release blogpost](https://falcon-lm.git
 
 - View [our release blogpost](https://falcon-lm.github.io/blog/falcon-h1/).
 - View [our technical report](https://arxiv.org/abs/2507.22448).
+- View [our official documentation](https://tiiuae.github.io/Falcon-H1/).
 - Feel free to join [our discord server](https://discord.gg/trwMYP9PYm) if you have any questions or to interact with our researchers and developers.
 
 # Citation