view article Article ChatML vs Harmony: Understanding the new Format from OpenAI π By kuotient β’ Aug 9 β’ 38
NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks Paper β’ 2410.20650 β’ Published Oct 28, 2024 β’ 17
Compact Language Models via Pruning and Knowledge Distillation Paper β’ 2407.14679 β’ Published Jul 19, 2024 β’ 38
Jamba: A Hybrid Transformer-Mamba Language Model Paper β’ 2403.19887 β’ Published Mar 28, 2024 β’ 111
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models Paper β’ 2404.02258 β’ Published Apr 2, 2024 β’ 107
Textbooks Are All You Need II: phi-1.5 technical report Paper β’ 2309.05463 β’ Published Sep 11, 2023 β’ 88
LLM papers Collection It is a collection of papers that are useful in studying LLM. β’ 14 items β’ Updated Apr 3, 2024 β’ 15