Transformers: Quadratic complexity AND LLMs: extended context window
Common descendants
4 Documents
Albert Gu sur X : "Quadratic attention has been indispensable for information-dense modalities such as language... until now..."
Tags:
2023-12-05 About
[2307.02486] LongNet: Scaling Transformers to 1,000,000,000 Tokens
Tags:
2023-07-06 About
Aran Komatsuzaki sur Twitter : "Unleashing Infinite-Length Input Capacity for Large-scale Language Models with Self-Controlled Memory System Enables LLMs to outperform ChatGPT in scenarios involving ultra-long document summarization or long-term conversations."
Tags:
2023-04-27 About
Aran Komatsuzaki sur Twitter : "Scaling Transformer to 1M tokens and beyond with Recurrent Memory Transformer..."
Tags:
2023-04-25 About