Meta

Meta Releases Llama 3.3 70B Surpassing 405B! Open Training Sparks Competition with Google and Musk

Meta's Llama 3.3 launches with 405B-level performance at a fraction of the cost, while Google’s Gemini reclaims the leaderboard crown. Explore the AI…

Dec 7 •

Unveiling the Secrets of LLaMA 3's Conversational Abilities(LLaMA 3 Practical 1)

Explore the capabilities of LLaMA 3, from NTP and stateful conversations to RAG and multi-agent collaboration. Learn how these features enhance LLM…

Dec 3 •

Ollama 0.4 Now Supports Building Llama 3.2 Vision + Visual RAG System

Ollama 0.4 now supports Llama 3.2 Vision for enhanced visual RAG retrieval. Discover its faster processing, improved OCR, and LocalGPT Vision…

Nov 10 •

Meta Releases Llama3.2 1B/3B Quantized Models: Accelerated Edge Inference, Reduced Memory Usage

Meta launches Llama3.2 quantized models with 2-4x faster inference and reduced memory usage, optimized for mobile devices.

Oct 25 •

LlamaCoder: A Brand New Open-Source AI Programming Assistant Based on Llama 3.1 405B

Discover LlamaCoder, a free, open-source AI coding assistant by Together AI, leveraging Meta's Llama 3.1 405B model to generate apps from text prompts…

Oct 19 •

Meta's Movie Gen Shocks the Scene with Video Generation, Audio Sync, and Editing

Meta's Movie Gen sets a new standard in AI video generation with advanced text-to-video, audio sync, and precise editing features, creating immersive…

Oct 5 •

Zuckerberg Confirms: Llama-4 Trained with 100,000 GPUs and Even Better Open-Source!

Meta's Mark Zuckerberg confirms Llama-4 was trained with over 100,000 GPUs, pushing AI boundaries. Plus, new open-source models like Llama-3.2 for…

Sep 27 •

Llama 3.2 is Here! Now Supports Image Inference and a Mobile Version!

Discover the latest updates from Meta's Llama models! Llama 3.2 introduces powerful image reasoning capabilities and lightweight versions for mobile…

Sep 26 •

Implementing Function Calling with Ollama, Llama 3.1, and Milvus

Enhance your AI apps with Llama 3.1, Milvus, and Function Calling. Learn to build context-aware, efficient solutions with simple steps.

Aug 27 •

Efficient Fine-Tuning of Llama 3.1 with Unsloth in Google Colab

Optimize Llama 3.1 with Unsloth in Google Colab: Efficient fine-tuning for superior performance and customization at a lower cost.

Aug 25 •

Using GraphRAG+LangChain+Ollama: LLama 3.1 Runs Integrated Knowledge Graph and Vector Database (Neo4j)

Learn how to use LLama 3.1 for GraphRAG operations in 50 lines of code. Integrate knowledge graphs and vector databases with Neo4j and LangChain.

Aug 8 •

Mastering Llama 3.1: Comprehensive Guide to Easy Local Deployment and Remote Usage

Llama 3.1 by Meta includes 8B, 70B, and 405B parameter models. Ensure your hardware meets the requirements for optimal performance. Install and use…

Aug 7 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts