2026-09-27 · America/Los_Angeles · 社区动态 · #2

Adding logit penalty for "wait", "maybe" and "perhaps" to Qwen models improves their accuracy

Meta came out with a banger paper https://arxiv.org/pdf/2606.00206, but it did not look at various quantizations supported in llama.cpp. So I did a run on 50 random MATH-500 questions (https://huggingface.co/datasets/HuggingFaceH4/MATH-500) and ran it on various quantizations of https://huggingface.co/bartowski/Qwen_Qwen3.5-4B-GGUF and tried --logit-bias 466-2 --logit-bias 694-2 --logit-bias 1362-2 \ --logit-bias 1412-2 --logit-bias 1921-2 --logit-bias 1990-2 \ --logit-bias 2086-2 --logit-bias 2361-2 --logit-bias 2441-2 \ --logit-bias 2493-2 --logit-bias 2892-2 --logit-bias 3222-2 \…

阅读原文查看评分、趋势与关联来源阅读整期日报

Adding logit penalty for "wait", "maybe" and "perhaps" to Qwen models improves their accuracy

热度 53.0 / 100；排名与评分保留该期记录。