Jun 07, 2023 · Open Source & Multimodal

Meet Falcon 2: TII Releases New AI Model Series, Outperforming Meta's New Llama 3

Next-gen Falcon 2 series launches AI model that is open-source, multilingual, and multimodal – with vision-to-language capabilities. Falcon 2 11B ranks No.1 globally, surpassing Meta's Llama 3 8B, as independently verified by the Hugging Face Leaderboard.

See the highlights
Multilingual Vision-to-language 11B & 11B VLM Runs on one GPU TII Falcon License 2.0
Falcon 2 soars

Falcon 2 Soars: Highlights

Next-Gen Falcon 2 Series launches AI Model that is Open-Source, Multilingual, and Multimodal – with Vision-to-Language Capabilities. Falcon 2 11B Ranks No.1 Globally, Surpassing Meta's Llama 3 8B, as Independently Verified by Hugging Face Leaderboard.

Highlight 1

Open-source, multilingual, and multimodal, and is the only AI model with vision-to-language capabilities.

Highlight 2

New Falcon 2 11B outperforms Meta's Llama 3 8B, and performs on par with the leading Google Gemma 7B model, as independently verified by the Hugging Face Leaderboard.

Highlight 3

Next up, we're looking to add 'Mixture of Experts' to enhance Falcon 2's capabilities even further.

What's New

Two ground-breaking versions of Falcon 2

Falcon 2 is our best performing model yet. We have released two ground-breaking versions:

Falcon 2 11B

A more efficient and accessible LLM trained on 5.5 trillion tokens with 11 billion parameters.

Falcon 2 11B VLM

Distinguished by its vision-to-language model (VLM) capabilities.

We are really excited about Falcon 2 11B VLM – it enables the seamless conversion of visual inputs into textual outputs. While both models are multilingual, notably, Falcon 2 11B VLM stands out as TII's first multimodal model – and the only one currently in the top tier market that has this image-to-text conversion capability, marking a significant advancement in AI innovation.
How can you use Falcon?

Released under the TII Falcon License 2.0

We have released Falcon 2 11B under the TII Falcon License 2.0, the permissive Apache 2.0-based software license which includes an acceptable use policy that promotes the responsible use of AI. More information on the new model can be found at FalconLLM.TII.ae.

How does the Falcon fare?

Falcon 2 11B performance and positioning

When tested against several prominent AI models in its class among pre-trained models, Falcon 2 11B surpasses the performance of Meta's newly launched Llama 3 with 8 billion parameters (8B), and performs on par with Google's Gemma 7B at first place, with a difference of only 0.01 average performance (Falcon 2 11B: 64.28 vs Gemma 7B: 64.29) according to the evaluation from Hugging Face.

64.28

Falcon 2 11B

Average performance on the Hugging Face Leaderboard

64.29

Google Gemma 7B

First place, a difference of only 0.01 average performance

More importantly, Falcon 2 11B and 11B VLM are both open-source, empowering developers worldwide with unrestricted access, without any limitations on usage of name at implementation.
Multilingual and Multimodal

Support across languages, text, and vision inputs

Falcon 2 11B models are equipped with multilingual capabilities to seamlessly tackle tasks in English, French, Spanish, German, Portuguese, and various other languages.

Languages

English, French, Spanish, German, Portuguese

Falcon 2 11B models are equipped with multilingual capabilities to seamlessly tackle tasks in English, French, Spanish, German, Portuguese, and various other languages.

Vision-to-language

Identify and interpret images and visuals

Falcon 2 11B VLM, a vision-to-language model also has the capability to identify and interpret images and visuals from the environment, providing a wide range of applications across industries such as healthcare, finance, e-commerce, education, and legal sectors.

Deployment

One GPU, lighter infrastructures

These models can run efficiently on just one graphics processing unit (GPU), making them highly scalable, and easy to deploy and integrate into lighter infrastructures like laptops and other devices.

HealthcareFinanceE-commerceEducationLegal sectorsDocument managementDigital archivingContext indexingSupporting individuals with visual impairments
Word of mouth

Falcon 2 in leadership views

With the release of Falcon 2 11B, we've introduced the first model in the Falcon 2 series. While Falcon 2 11B has demonstrated outstanding performance, we reaffirm our commitment to the open-source movement with it, and to the Falcon Foundation. With other multimodal models soon coming to the market in various sizes, our aim is to ensure that developers and entities that value their privacy, have access to one of the best AI models to enable their AI journey.
H.E. Faisal Al BannaiSecretary General of ATRC and Strategic Research and Advanced Technology Affairs Advisor to the UAE President
AI is continually evolving, and developers are recognizing the myriad benefits of smaller, more efficient models. In addition to reducing computing power requirements and meeting sustainability criteria, these models offer enhanced flexibility, seamlessly integrating into edge AI infrastructure, the next emerging megatrend. Furthermore, the vision-to-language capabilities of Falcon 2 open new horizons for accessibility in AI, empowering users with transformative image to text interactions.
Dr. Hakim HacidExecutive Director and Acting Chief Researcher of the AI Cross-Center Unit at TII
What's Next

Mixture of Experts and deeper multimodal adaptation

Up next, Falcon 2 models will be further enhanced with advanced machine learning capabilities like 'Mixture of Experts' (MoE), aimed at pushing their performance to even more sophisticated levels.

This method involves amalgamating smaller networks with distinct specializations, ensuring that the most knowledgeable domains collaborate to deliver highly sophisticated and customized responses – almost like having a team of smart helpers who each know something different and work together to predict or make decisions when needed.

This approach not only improves accuracy, but it also accelerates decision-making, paving the way for more intelligent and efficient AI systems.

Watch this space...

Frequently asked questions

Falcon 2 FAQ

Answers below are drawn from the Falcon 2 announcement and licensing terms. For comprehensive information, always refer to the full License Agreement.

What is Falcon 2?+

Falcon 2 is our best performing model yet. We have released two ground-breaking versions: Falcon 2 11B, a more efficient and accessible LLM trained on 5.5 trillion tokens with 11 billion parameters, and Falcon 2 11B VLM, distinguished by its vision-to-language model (VLM) capabilities.

What is the difference between Falcon 2 11B and Falcon 2 11B VLM?+

Falcon 2 11B and 11B VLM are both open-source, empowering developers worldwide with unrestricted access, without any limitations on usage of name at implementation. Falcon 2 11B VLM enables the seamless conversion of visual inputs into textual outputs and stands out as TII’s first multimodal model.

Can I use Falcon 2 in commercial products?+

We have released Falcon 2 11B under the TII Falcon License 2.0, the permissive Apache 2.0-based software license which includes an acceptable use policy that promotes the responsible use of AI.

Does Falcon 2 support multiple languages?+

Falcon 2 11B models are equipped with multilingual capabilities to seamlessly tackle tasks in English, French, Spanish, German, Portuguese, and various other languages.

How much hardware does Falcon 2 need?+

These models can run efficiently on just one graphics processing unit (GPU), making them highly scalable, and easy to deploy and integrate into lighter infrastructures like laptops and other devices.

What is next for Falcon 2?+

Up next, Falcon 2 models will be further enhanced with advanced machine learning capabilities like 'Mixture of Experts' (MoE), aimed at pushing their performance to even more sophisticated levels.

Try it for yourself here

Sign in with Google to check your account, or pick a plan to start with Falcon 2 credits.

Read the highlights
Falcon 2 — Open-Source Multilingual Multimodal AI Model Series