final-report-169449903.pdf
web.stanford.edu · 5,773 words · saved by 1 readers
N/A
Nano Backpack Language Model on Chinese Characters Stanford CS224N Custom Project Hao Sun Stanford University haosun@stanford.edu Abstract This project focuses on the Backpack Language Model proposed in the paper "Backpack Language Models" [1], which aims to improve lexical representations and non-contextual controllability in language…
related reading
- Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
- [2005.14165] Language Models are Few-Shot Learnersarxiv.org
- Recursive Language Models | Alex L. Zhangalexzhang13.github.io
- A History of Large Language Modelsgregorygundersen.com
- 1301.3781arxiv.org
- Language Modelinglena-voita.github.io
- [2112.10508] Between words and characters: A Brief History of Open-Vocabulary Modeling and Tokenization in NLParxiv.org
- Generalized Language Models | Lil'Loglilianweng.github.io
- Language Models, World Models, and Human Model-Buildinglingo.csail.mit.edu
- GenAI Handbookgenai-handbook.github.io
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
- What language do language models speak?tcz.hu