There are a lot of questions and misconceptions about open weight models. I break it all down here so even nontechnical folks can understand.
CJ (Coding Garden)
@CodingGarden
Senior Creator at @syntaxfm / @getsentry
Host of Coding Garden on Twitch and YouTube
Co-organizer of @DenverScript
w3cj.com
- LLM tool calls explained, excerpt from my video "I Built an LLM From Scratch"
- The full pipeline of LLMs explained, excerpt from my video "I Built an LLM From Scratch"
- i for one welcome our new robot overlords
- The output of a transformer (LLM) is a score (logit) for every possible next token. We then use temperature, softmax, top-p and sampling to choose the next token, excerpt from my video "I Built an LLM From Scratch"
