Thomas Wolf：AI 研究员尝试将 lm_head 量化至 4 位
中文全文 · AI 翻译
我的 AGI 标准仍然是一个 AI 赢得诺贝尔奖。
但一个 AI 研究员看着 lm_head（每个人都告诉你保持高精度）决定将其量化为 4 位，并且实际上是正确的（与 bf16 相差 0.7 个点），这绝对令人印象深刻。
当结果是开放权重推送到 Hugging Face hub 时，那就更好了。
恭喜 @Recursive_SI ！
对照原文
My bar for AGI is still an AI winning a Nobel. But an AI researcher looking at the lm_head (that *everyone* tells you to keep in high precision) deciding to quantize it to 4 bits AND being actually right (0.7pt from bf16) is definitely impressive. Even better when the result are open-weights pushed on the Hugging Gace hub. Congrats @Recursive_SI !