Doubt

https://jalammar.github.io/illustrated-transformer/

https://goyalpramod.github.io/blogs/Transformers_laid_out/

https://freedium.cfd/https://medium.com/@cristianleo120/the-math-behind-transformers-6d7710682a1f#fab7

https://data-science-blog.com/blog/2021/04/07/multi-head-attention-mechanism/

https://www.youtube.com/watch?v=OyFJWRnt_AY

https://aman.ai/primers/ai/transformers/

https://cohere.com/llmu?_gl=1*12sy2jt*_ga*NTI4ODgwMDk3LjE3NDMwMDA0MjU.*_ga_CRGS116RZS*MTc0MzAwMDQyNC4xLjAuMTc0MzAwMDQyOS41OS4wLjA.*_gcl_au*MTA2NDYxMTU1LjE3NDMwMDA0Mjk

https://github.com/Denis2054/Transformers-for-NLP-2nd-Edition