Thanks a lot for taking the time to compile this. Maybe create something like a docs page that would make it easier to see the answer to the questions and self-host this with GitHub pages. You got a star from me though :D
Seems very oriented toward model architecture and inference engineering. Maybe add some more on model training flow, distillation, data generation, SFT and RL techniques?
Thanks a lot for taking the time to compile this. Maybe create something like a docs page that would make it easier to see the answer to the questions and self-host this with GitHub pages. You got a star from me though :D
Seems very oriented toward model architecture and inference engineering. Maybe add some more on model training flow, distillation, data generation, SFT and RL techniques?