Tags

transformers

Transformer architecture and attention

Topics

• TransformersThe transformer is the neural network architecture behind nearly every modern LLM. It was introduced in 2017 for translation and replaced recurrent networks because attention can process a whole…

Sources

• Qwen3.8-Flash-Next model cardrelease · Alibaba Qwen team · 26 August 2026
• DeepSeek-V4.1-Flash: Smarter, Faster, More Efficientrelease · DeepSeek · 10 September 2026
• Qwen3.5-397B-A17B model cardrelease · Alibaba Qwen team · 16 February 2026
• DeepSeek-V4-Pro model cardrelease · DeepSeek · 24 April 2026
• Attention Is All You Needpaper · Vaswani et al. (Google Brain, Google Research) · 12 June 2017