Adding logit penalty for "wait", "maybe" and "perhaps" to Qwen models improves their accuracy
英文标题：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.
打开原文相关 2 · 机会 0
中文
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.
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
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.