Slacker News Slacker News logo featuring a lazy sloth with a folded newspaper hat
  • top
  • new
  • show
  • ask
  • jobs
Library

Comment by liuliu

8 days ago

Note that 3.5 9B cannot do thinking (while 3.6 27B can, pretty effectively, quite verbosely).

3 comments

liuliu

Reply

gunalx  8 days ago

3.5 9B can do thinking. Its just disabled by default in its gguf chat template.

  • liuliu  8 days ago

    It is disabled because it doesn't work :) Try it and see the doom loop it gets itself in.

    • b89kim  8 days ago

      I had no failure mode in 3.6 9B thinking with llama.cpp. After release, there were updates for both model and llama.cpp.

Slacker News

Product

  • API Reference
  • Hacker News RSS
  • Source on GitHub

Community

  • Support Ukraine
  • Equal Justice Initiative
  • GiveWell Charities