Mex Ivanov

MexIvanov

AI & ML interests

NLP, Coding, Quantum Computing and more.

Recent Activity

reacted to singhsidhukuldeep's post with šŸ”„ about 14 hours ago
Exciting News in AI: JinaAI Releases JINA-CLIP-v2! The team at Jina AI has just released a groundbreaking multilingual multimodal embedding model that's pushing the boundaries of text-image understanding. Here's why this is a big deal: šŸš€ Technical Highlights: - Dual encoder architecture combining a 561M parameter Jina XLM-RoBERTa text encoder and a 304M parameter EVA02-L14 vision encoder - Supports 89 languages with 8,192 token context length - Processes images up to 512Ɨ512 pixels with 14Ɨ14 patch size - Implements FlashAttention2 for text and xFormers for vision processing - Uses Matryoshka Representation Learning for efficient vector storage āš”ļø Under The Hood: - Multi-stage training process with progressive resolution scaling (224ā†’384ā†’512) - Contrastive learning using InfoNCE loss in both directions - Trained on massive multilingual dataset including 400M English and 400M multilingual image-caption pairs - Incorporates specialized datasets for document understanding, scientific graphs, and infographics - Uses hard negative mining with 7 negatives per positive sample šŸ“Š Performance: - Outperforms previous models on visual document retrieval (52.65% nDCG@5) - Achieves 89.73% image-to-text and 79.09% text-to-image retrieval on CLIP benchmark - Strong multilingual performance across 30 languages - Maintains performance even with 75% dimension reduction (256D vs 1024D) šŸŽÆ Key Innovation: The model solves the long-standing challenge of unifying text-only and multi-modal retrieval systems while adding robust multilingual support. Perfect for building cross-lingual visual search systems! Kudos to the research team at Jina AI for this impressive advancement in multimodal AI!
reacted to singhsidhukuldeep's post with šŸš€ 2 days ago
Exciting breakthrough in AI: @Meta's new Byte Latent Transformer (BLT) revolutionizes language models by eliminating tokenization! The BLT architecture introduces a groundbreaking approach that processes raw bytes instead of tokens, achieving state-of-the-art performance while being more efficient and robust. Here's what makes it special: >> Key Innovations Dynamic Patching: BLT groups bytes into variable-sized patches based on entropy, allocating more compute power where the data is more complex. This results in up to 50% fewer FLOPs during inference compared to traditional token-based models. Three-Component Architecture: ā€¢ Lightweight Local Encoder that converts bytes to patch representations ā€¢ Powerful Global Latent Transformer that processes patches ā€¢ Local Decoder that converts patches back to bytes >> Technical Advantages ā€¢ Matches performance of Llama 3 at 8B parameters while being more efficient ā€¢ Superior handling of non-English languages and rare character sequences ā€¢ Remarkable 99.9% accuracy on spelling tasks ā€¢ Better scaling properties than token-based models >> Under the Hood The system uses an entropy model to determine patch boundaries, cross-attention mechanisms for information flow, and hash n-gram embeddings for improved representation. The architecture allows simultaneous scaling of both patch and model size while maintaining fixed inference costs. This is a game-changer for multilingual AI and could reshape how we build future language models. Excited to see how this technology evolves!
liked a model 7 days ago
CohereForAI/c4ai-command-r7b-12-2024
View all activity

Organizations

None yet