alt Hacker NewsExactly, DeepSeek, Qwen etc are catching the attention because they put out their tech docs and papers, so we can read about how the models work and what they think their innovation was this time.
Exactly, DeepSeek, Qwen etc are catching the attention because they put out their tech docs and papers, so we can read about how the models work and what they think their innovation was this time.
Do they publish their distillation strategies on the private frontier models? Just curious.