Running 58 AmphibiousRizz LoRA Browser πΈ 58 Visual browser for amphibiousrizz's Krea 2 character LoRAs
It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization Paper β’ 2504.13173 β’ Published Apr 17, 2025 β’ 21
Tensor Product Attention Is All You Need Paper β’ 2501.06425 β’ Published Jan 11, 2025 β’ 91 β’ 5
Running 4.07k The Ultra-Scale Playbook π 4.07k The ultimate guide to training LLM on large GPU Clusters
Adapting LLMs to Hebrew: Unveiling DictaLM 2.0 with Enhanced Vocabulary and Instruction Capabilities Paper β’ 2407.07080 β’ Published Jul 9, 2024 β’ 22
Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters Paper β’ 2406.16758 β’ Published Jun 24, 2024 β’ 20
Pile-T5 Collection T5 trained on the Pile with Llama Tokenizer β’ 4 items β’ Updated 23 days ago β’ 18
Running on CPU Upgrade 14.1k Open LLM Leaderboard π 14.1k Track, rank and evaluate open LLMs and chatbots