4mo ago

QwQ-32B: Embracing the Power of Reinforcement Learning

qwenlm.github.io

Comments

Technology @lemmy.ml

☆ Yσɠƚԋσʂ ☆ @lemmy.ml

4mo ago

QwQ-32B is a 32 billion parameter language model achieves comparable performance to DeepSeek-R1 with 671 billion parameters, using reinforcement learning for scaling

qwenlm.github.io /blog/qwq-32b/

Technology @lemmygrad.ml

☆ Yσɠƚԋσʂ ☆ @lemmygrad.ml

4mo ago

QwQ-32B is a 32 billion parameter language model achieves comparable performance to DeepSeek-R1 with 671 billion parameters, using reinforcement learning for scaling

qwenlm.github.io /blog/qwq-32b/

No comments