Technology Innovation Institute

company

https://www.tii.ae/

AI & ML interests

Large language models

Recent Activity

ybelkada updated a Space 9 days ago

tiiuae/e2lmc-blog

ybelkada updated a model 9 days ago

tiiuae/Falcon3-10B-Base-1.58bit-prequantized

ybelkada published a model 9 days ago

tiiuae/Falcon3-10B-Base-1.58bit-prequantized

View all activity

Papers

Falcon Perception

Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers

View all Papers

Articles

QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard

Falcon Perception

Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMs

Introducing Falcon H1R 7B

Introducing Falcon-H1-Arabic: Pushing the Boundaries of Arabic Language AI with Hybrid Architecture

📚 3LM: A Benchmark for Arabic LLMs in STEM and Code

Announcing NeurIPS 2025 E2LM Competition: Early Training Evaluation of Language Models

Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance

Falcon-Arabic: A Breakthrough in Arabic Language Models

Falcon-Edge: A series of powerful, universal, fine-tunable 1.58bit language models.

View all articles

updated a Space 9 days ago

E2LM: Early Training Evaluation of Language Models - building new scientific benchmarks for Small Language Models with the community

Explore interactive LLM evaluation charts for early-stage training

updated a model 9 days ago

tiiuae/Falcon3-10B-Base-1.58bit-prequantized

Text Generation • 10B • Updated 9 days ago • 277

published a model 9 days ago

tiiuae/Falcon3-10B-Base-1.58bit-prequantized

Text Generation • 10B • Updated 9 days ago • 277

updated a collection 10 days ago

E2LMC: Early-stage Evaluation for LLM Training Competition

Collection of artifacts from the E2LM NeurIPS 2025 competition • 7 items • Updated 2 days ago

published a Space 10 days ago

E2LM: Early Training Evaluation of Language Models - building new scientific benchmarks for Small Language Models with the community

Explore interactive LLM evaluation charts for early-stage training

updated a collection 10 days ago

E2LMC: Early-stage Evaluation for LLM Training Competition

Collection of artifacts from the E2LM NeurIPS 2025 competition • 7 items • Updated 2 days ago

updated a collection 17 days ago

Falcon Edge series

A series of powerful, universal and fine-tunable small Language Models • 8 items • Updated 17 days ago • 25

updated a model 17 days ago

tiiuae/Falcon-E-3B-Base-prequantized

Text Generation • 3B • Updated 17 days ago • 332

published a model 17 days ago

tiiuae/Falcon-E-3B-Base-prequantized

Text Generation • 3B • Updated 17 days ago • 332

published an article 18 days ago

Article

QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard

18 days ago

•

11

updated a collection 29 days ago

SigLino: Vision Foundation Models (SigLIP2 + DINOv3)

Vision encoders distilled from DINOv3 and SigLIP2 (MoE & Dense). CVPR 2026. • 6 items • Updated 29 days ago • 17

in tiiuae/Falcon-Perception 29 days ago

[Solved] Unable to run test example (Torch OOM)

#1 opened about 1 month ago by

FalconPerception

in tiiuae/Falcon-OCR about 1 month ago

Discussion: Highlighting PP-DocLayoutV3's contribution in your project

#11 opened about 1 month ago by

Finetuning method

#10 opened about 1 month ago by

in tiiuae/siglino-0.6B about 1 month ago

Update to image feature extraction

#2 opened about 1 month ago by