HN Explorer

kisjovan

↗ HN profile [ 33.9 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: Swift-Qwen3.8-27B, -58.3% thinking, x1.95 speed, accuracy of xhigh (huggingface.co)

    Hi everybody, we post-trained Qwen 3.8 27B to be more efficient by figuring out which tokens were linked to overthinking and penalizing them without "attacking" the reasoning length directly then fixed the accuracy with…

    2 points 10