Quick recap on the state of language model reasoning

Поділитися
Вставка
  • Опубліковано 6 січ 2025

КОМЕНТАРІ •

  • @bob-007
    @bob-007 4 дні тому +5

    First! :)

  • @TheFireHacker
    @TheFireHacker 4 дні тому +1

    12:12 "This something we did in our project" are you talking about allenai open instruct cot model which is on Hugginface?

    • @interconnects
      @interconnects  4 дні тому +1

      Tulu 3 is trained with RLVR, but its a general chat model not a reasoning focused model.