Post
593
🚀 Meta’s Llama 4 Models Now on Hugging Face!
Meta has released Llama 4 Scout and Llama 4 Maverick, now available on Hugging Face:
• Llama 4 Scout: 17B active parameters, 16-expert Mixture of Experts (MoE) architecture, 10M token context window, fits on a single H100 GPU. 
• Llama 4 Maverick: 17B active parameters, 128-expert MoE architecture, 1M token context window, optimized for DGX H100 systems. 
🔥 Key Features:
• Native Multimodality: Seamlessly processes text and images. 
• Extended Context Window: Up to 10 million tokens for handling extensive inputs.
• Multilingual Support: Trained on 200 languages, with fine-tuning support for 12, including Arabic, Spanish, and German. 
🛠️ Access and Integration:
• Model Checkpoints: Available under the meta-llama organization on the Hugging Face Hub.
• Transformers Compatibility: Fully supported in transformers v4.51.0 for easy loading and fine-tuning.
• Efficient Deployment: Supports tensor-parallelism and automatic device mapping.
These models offer developers enhanced capabilities for building sophisticated, multimodal AI applications. 
Meta has released Llama 4 Scout and Llama 4 Maverick, now available on Hugging Face:
• Llama 4 Scout: 17B active parameters, 16-expert Mixture of Experts (MoE) architecture, 10M token context window, fits on a single H100 GPU. 
• Llama 4 Maverick: 17B active parameters, 128-expert MoE architecture, 1M token context window, optimized for DGX H100 systems. 
🔥 Key Features:
• Native Multimodality: Seamlessly processes text and images. 
• Extended Context Window: Up to 10 million tokens for handling extensive inputs.
• Multilingual Support: Trained on 200 languages, with fine-tuning support for 12, including Arabic, Spanish, and German. 
🛠️ Access and Integration:
• Model Checkpoints: Available under the meta-llama organization on the Hugging Face Hub.
• Transformers Compatibility: Fully supported in transformers v4.51.0 for easy loading and fine-tuning.
• Efficient Deployment: Supports tensor-parallelism and automatic device mapping.
These models offer developers enhanced capabilities for building sophisticated, multimodal AI applications.