Capital de TokensOne trillion parameters, but only 49 billion per query
Watch on YouTube The trillion describes the model’s total size. The forty-nine billion describes the parameters that, according to Mistral, are activated per query. AI Weekly explains that this brings the computational cost of each response close to that of a dense forty-nine-billion-parameter model. It does not mean that storing the entire model co
The trillion describes the model’s total size. The forty-nine billion describes the parameters that, according to Mistral, are activated per query. AI Weekly explains that this brings the computational cost of each response close to that of a dense forty-nine-billion-parameter model. It does not mean that storing the entire model or having the infrastructure to run it costs the same. The parameters that are not used in a query remain part of the system.
Full episode: https://youtu.be/3sNB5QRQ95g
🤖 AI-generated content: the script, voices, and images in this episode were produced using artificial intelligence tools.
#Shorts