Comment by sigmoid10
1 day ago
Sounds a lot like an autoregressive sampling problem. Maybe try to set temperature and repeat penalty differently.
1 day ago
Sounds a lot like an autoregressive sampling problem. Maybe try to set temperature and repeat penalty differently.
You're right, I should have checked the model settings. For some reason the default model profile in Ollama had temperature set to 0. Changing the temperature and repeat penalty worked much better than it did when I tried to correct similar behavior in the smallest phi4 reasoning model.
Thank you, this was affecting me too.