google/embeddinggemma-2
Feature Extraction • 0.7B • Updated • 116k • • 1.93k
Klimenty Titov
markcda
AI & ML interests
None yet
Recent Activity
liked a model about 21 hours ago
google/embeddinggemma-2 liked a model 3 months ago
Cactus-Compute/needle liked a model 4 months ago
JetBrains/Mellum2-12B-A2.5B-InstructOrganizations
None yet
liked a
model about 21 hours ago
liked a
model 3 months ago
liked 2
models 4 months ago
liked 4
models 6 months ago
openai/privacy-filter
Token Classification • 1B • Updated • 331k • • 1.79k
unsloth/gemma-4-E4B-it-GGUF
Image-Text-to-Text • 8B • Updated • 594k • 647
unsloth/gemma-4-26B-A4B-it-GGUF
Image-Text-to-Text • 25B • Updated • 729k • 1.21k
Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF
Image-Text-to-Text • 9B • Updated • 19.9k • 397
liked a
model 7 months ago
liked a
model almost 2 years ago
liked a
model over 2 years ago
liked a
Space over 2 years ago
reacted to DmitryRyumin's post with 🔥 over 2 years ago
Post
1915
🔥🚀🌟 New Research Alert - YOCO! 🌟🚀🔥
📄 Title: You Only Cache Once: Decoder-Decoder Architectures for Language Models 🔝
📝 Description: YOCO is a novel decoder-decoder architecture for LLMs that reduces memory requirements, speeds up prefilling, and maintains global attention. It consists of a self-decoder for encoding KV caches and a cross-decoder for reusing these caches via cross-attention.
👥 Authors: Yutao Sun et al.
📄 Paper: You Only Cache Once: Decoder-Decoder Architectures for Language Models (2405.05254)
📁 Repository: https://github.com/microsoft/unilm/tree/master/YOCO
📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
🔍 Keywords: #YOCO #DecoderDecoder #LargeLanguageModels #EfficientArchitecture #GPUMemoryReduction #PrefillingSpeedup #GlobalAttention #DeepLearning #Innovation #AI
📄 Title: You Only Cache Once: Decoder-Decoder Architectures for Language Models 🔝
📝 Description: YOCO is a novel decoder-decoder architecture for LLMs that reduces memory requirements, speeds up prefilling, and maintains global attention. It consists of a self-decoder for encoding KV caches and a cross-decoder for reusing these caches via cross-attention.
👥 Authors: Yutao Sun et al.
📄 Paper: You Only Cache Once: Decoder-Decoder Architectures for Language Models (2405.05254)
📁 Repository: https://github.com/microsoft/unilm/tree/master/YOCO
📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
🔍 Keywords: #YOCO #DecoderDecoder #LargeLanguageModels #EfficientArchitecture #GPUMemoryReduction #PrefillingSpeedup #GlobalAttention #DeepLearning #Innovation #AI
- 3 replies
liked a
model over 2 years ago
liked 2
models almost 3 years ago
