| ▲ | sosodev 4 hours ago | |
They reference https://thinkingmachines.ai/blog/on-policy-distillation/ If I understand correctly, it's distillation via having a teacher model score each of the student's tokens for a problem based on their own probabilities of generating that token at each step in the sequence. The reward/loss is then applied as RL. The multi-teacher bit seems to imply they're distilling from multiple models. It's light on the details, but it seems like it could be part of distilling from frontier/closed models. Provided they calculate the logprobs, which OpenAI seems to allow via API but not Anthropic. Maybe they have a way of estimating the logprobs externally? This method can be used to learn any domain from the teacher. Biology included. | ||
| ▲ | htrp 2 hours ago | parent | next [-] | |
> which OpenAI seems to allow via API but not Anthropic Does openai still allow logprobs in their current gen models? | ||
| ▲ | mike_hearn 4 hours ago | parent | prev [-] | |
It's not that light on the details. I read the paper and they train several different models in parallel over a few different domains and then they distill from their own models to get the final model. | ||