Llama 3.2 released: Multimodal, 1B to 90B sizes
Llama 3.2 has been released as an open-source AI model in various sizes for text and image processing, enhancing application development and gaining significant traction with over 350 million downloads.
Read original article
Llama 3.2 has been released as an open-source AI model, offering various sizes including 1B, 3B, 11B, and 90B. The 1B and 3B models are designed for multilingual text processing, while the 11B and 90B models can handle both text and image inputs. This release aims to enhance the development of efficient applications, particularly for on-device use, such as summarizing discussions or processing images. The Llama Stack provides a streamlined developer experience, allowing for quick application development in multiple programming languages, including Python and Swift. The models have been evaluated against over 150 benchmark datasets, demonstrating strong performance in various tasks. Llama models have gained significant traction, with over 350 million downloads on Hugging Face, indicating their popularity in the open-source community. Partnerships with companies like ARM, MediaTek, and Dell are facilitating the integration of Llama models into mobile and edge devices, promoting the adoption of AI in enterprise applications. The Llama Stack is positioned to simplify AI application development across diverse use cases, enhancing productivity and collaboration in various industries.
- Llama 3.2 offers models in multiple sizes for text and image processing.
- The Llama Stack simplifies application development and supports various programming languages.
- Over 350 million downloads highlight the popularity of Llama models in the open-source community.
- Partnerships with tech companies enhance the deployment of Llama models on mobile and edge devices.
- The release aims to improve AI application development across various enterprise use cases.
Related
Llama 3.1 Official Launch
Llama introduces Llama 3.1, an open-source AI model available in 8B, 70B, and 405B versions. The 405B model is highlighted for its versatility in supporting various use cases, including multi-lingual agents and analyzing large documents. Users can leverage coding assistants, real-time or batch inference, and fine-tuning capabilities. Llama emphasizes open-source AI and offers subscribers updates via a newsletter.
Llama 3.1: Our most capable models to date
Meta has launched Llama 3.1 405B, an advanced open-source AI model supporting diverse languages and extended context length. It introduces new features like Llama Guard 3 and aims to enhance AI applications with improved models and partnerships.
Why Llama 3.1 is Important
Meta's new Llama 3.1 405B model prioritizes data sovereignty, open-source accessibility, cost savings, independence, and advanced customization. It aims to boost AI innovation by empowering companies with control and flexibility.
An update on Llama adoption
Llama, Meta's language model, has surpassed 350 million downloads, with significant growth in usage and adoption among major companies, driven by its open-source nature and recent enhancements.
Llama 3.2: Revolutionizing edge AI and vision with open, customizable models
Meta released Llama 3.2, featuring vision models with 11B and 90B parameters, and lightweight text models with 1B and 3B parameters, optimized for edge devices and supporting extensive deployment options.
8 comments* Llama 3.2 multimodal actually still ranks below Molmo from ai2 released this morning.
* AI2D: 92.3 (3.2 90B) vs 96.3 (of Molmo 72B)
* Llama 3.2 1B and 3B is pruned from 3.1 8B so no leapfrogging unlike 3 -> 3.1.
* Notably no code benchmarks. Deliberate exclusion of code data in distillation to maximize mobile on-device use cases?
Was hoping there would be some interesting models I can add to https://double.bot but doesn't seem like any improvements to frontier performance on coding.
Related
Llama 3.1 Official Launch
Llama introduces Llama 3.1, an open-source AI model available in 8B, 70B, and 405B versions. The 405B model is highlighted for its versatility in supporting various use cases, including multi-lingual agents and analyzing large documents. Users can leverage coding assistants, real-time or batch inference, and fine-tuning capabilities. Llama emphasizes open-source AI and offers subscribers updates via a newsletter.
Llama 3.1: Our most capable models to date
Meta has launched Llama 3.1 405B, an advanced open-source AI model supporting diverse languages and extended context length. It introduces new features like Llama Guard 3 and aims to enhance AI applications with improved models and partnerships.
Why Llama 3.1 is Important
Meta's new Llama 3.1 405B model prioritizes data sovereignty, open-source accessibility, cost savings, independence, and advanced customization. It aims to boost AI innovation by empowering companies with control and flexibility.
An update on Llama adoption
Llama, Meta's language model, has surpassed 350 million downloads, with significant growth in usage and adoption among major companies, driven by its open-source nature and recent enhancements.
Llama 3.2: Revolutionizing edge AI and vision with open, customizable models
Meta released Llama 3.2, featuring vision models with 11B and 90B parameters, and lightweight text models with 1B and 3B parameters, optimized for edge devices and supporting extensive deployment options.