Introducing Falcon ASR
• 28
AI & ML interests
Large language models
Recent Activity
View all activity
Papers
View all Papers Articles
Falcon-Perception and Falcon-OCR model: early-fusion, natively multimodal, dense Autoregressive Transformer models.
Collection of artifacts from the E2LM NeurIPS 2025 competition
-
E2LM: Early Training Evaluation of Language Models - building new scientific benchmarks for Small Language Models with the community
📝5Explore interactive LLM evaluation charts for early-stage training
-
tiiuae/dense-500m-arch1
Updated • 2 -
tiiuae/dense-500m-arch2
Updated -
tiiuae/dense-1b-arch1
Updated
7B models built on top of Falcon3-7B
Arabic benchmark datasets https://arxiv.org/pdf/2507.15850
This collection features the FalconMamba 7B base model, the instruction-tuned version, their 4-bit and GGUF variants, and the demo.
-
Falcon Mamba Playground
🐍65Generate chat responses using FalconMamba-7b model
-
Falcon Mamba: The First Competitive Attention-free 7B Language Model
Paper • 2410.05355 • Published • 38 -
tiiuae/falcon-mamba-7b
Text Generation • 7B • Updated • 16.1k • 248 -
tiiuae/falcon-mamba-7b-instruct
Text Generation • 7B • Updated • 3.9k • 74
Leveraging Contextual Web Data for Fine-tuning Vision Language Models (https://arxiv.org/abs/2502.10250)
Vision encoders distilled from DINOv3 and SigLIP2 (MoE & Dense), and the OpenLVD-200M training data. CVPR 2026.
A series of extremely small, yet powerful language models redefining capabilities at small scale
-
Falcon-H1-Tiny: A series of extremely small, yet powerful language models redefining capabilities at small scale
📝49Generate text using extremely small yet powerful language models
-
Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers
Paper • 2601.04890 • Published • 45 -
tiiuae/Falcon-H1-Tiny-90M-Instruct
Text Generation • 91.1M • Updated • 1.76k • 48 -
tiiuae/Falcon-H1-Tiny-90M-Instruct-GGUF
91.1M • Updated • 4.89k • 25
Falcon-H1 Family of Hybrid-Head Language Models (Transformer-SSM), including 0.5B, 1.5B, 1.5B-Deep, 3B, 7B, and 34B (pretrained & instruction-tuned).
-
Falcon H1 Playground
🦅34Chat with Falcon-H1 language models
-
Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance
Paper • 2507.22448 • Published • 72 -
Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers
Paper • 2601.04890 • Published • 45 -
tiiuae/Falcon-H1-0.5B-Base
Text Generation • 0.5B • Updated • 28.5k • 17
A series of powerful, universal and fine-tunable small Language Models
Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters.
-
The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only
Paper • 2306.01116 • Published • 45 -
tiiuae/falcon-refinedweb
Viewer • Updated • 968M • 35.9k • 976 -
tiiuae/falcon-rw-1b
Text Generation • Updated • 6.9k • 119 -
tiiuae/falcon-rw-7b
Text Generation • 8B • Updated • 873 • 18
Falcon-Perception and Falcon-OCR model: early-fusion, natively multimodal, dense Autoregressive Transformer models.
Vision encoders distilled from DINOv3 and SigLIP2 (MoE & Dense), and the OpenLVD-200M training data. CVPR 2026.
Collection of artifacts from the E2LM NeurIPS 2025 competition
-
E2LM: Early Training Evaluation of Language Models - building new scientific benchmarks for Small Language Models with the community
📝5Explore interactive LLM evaluation charts for early-stage training
-
tiiuae/dense-500m-arch1
Updated • 2 -
tiiuae/dense-500m-arch2
Updated -
tiiuae/dense-1b-arch1
Updated
A series of extremely small, yet powerful language models redefining capabilities at small scale
-
Falcon-H1-Tiny: A series of extremely small, yet powerful language models redefining capabilities at small scale
📝49Generate text using extremely small yet powerful language models
-
Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers
Paper • 2601.04890 • Published • 45 -
tiiuae/Falcon-H1-Tiny-90M-Instruct
Text Generation • 91.1M • Updated • 1.76k • 48 -
tiiuae/Falcon-H1-Tiny-90M-Instruct-GGUF
91.1M • Updated • 4.89k • 25
Falcon-H1 Family of Hybrid-Head Language Models (Transformer-SSM), including 0.5B, 1.5B, 1.5B-Deep, 3B, 7B, and 34B (pretrained & instruction-tuned).
-
Falcon H1 Playground
🦅34Chat with Falcon-H1 language models
-
Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance
Paper • 2507.22448 • Published • 72 -
Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers
Paper • 2601.04890 • Published • 45 -
tiiuae/Falcon-H1-0.5B-Base
Text Generation • 0.5B • Updated • 28.5k • 17
7B models built on top of Falcon3-7B
A series of powerful, universal and fine-tunable small Language Models
Arabic benchmark datasets https://arxiv.org/pdf/2507.15850
Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters.
This collection features the FalconMamba 7B base model, the instruction-tuned version, their 4-bit and GGUF variants, and the demo.
-
Falcon Mamba Playground
🐍65Generate chat responses using FalconMamba-7b model
-
Falcon Mamba: The First Competitive Attention-free 7B Language Model
Paper • 2410.05355 • Published • 38 -
tiiuae/falcon-mamba-7b
Text Generation • 7B • Updated • 16.1k • 248 -
tiiuae/falcon-mamba-7b-instruct
Text Generation • 7B • Updated • 3.9k • 74
-
The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only
Paper • 2306.01116 • Published • 45 -
tiiuae/falcon-refinedweb
Viewer • Updated • 968M • 35.9k • 976 -
tiiuae/falcon-rw-1b
Text Generation • Updated • 6.9k • 119 -
tiiuae/falcon-rw-7b
Text Generation • 8B • Updated • 873 • 18
Leveraging Contextual Web Data for Fine-tuning Vision Language Models (https://arxiv.org/abs/2502.10250)