Haiyang-W/TokenFormer · AI Repo StatsHAHaiyang-W/TokenFormer
[ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
LLM & mô hình nền tảngPython Apache-2.0 42tạo 2024-10-29 #architecture#attention-mechanism#foundation-models#llm#scaling-methods#transformer