T-FREE: Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings Paper β’ 2406.19223 β’ Published Jun 27 β’ 8
LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models Paper β’ 2405.18377 β’ Published May 28 β’ 18
Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory Paper β’ 2405.08707 β’ Published May 14 β’ 27
Phi-3 Collection Phi-3 family of small language and multi-modal models. Language models are available in short- and long-context lengths. β’ 26 items β’ Updated 8 days ago β’ 497
Llamafied Models Collection This is a collection of llamafied models - such as Qwen. β’ 5 items β’ Updated Apr 19 β’ 1