Thomas Wolf· @Thom_Wolf · X·· 2 小时前AI 评分52
AI 导读
Richard Socher 发布 Recursive 首个模型 Flint，一个由 Eureka Machine 自动研究系统构建的快速本地编码模型，MacBook Pro 上可达 125+ tokens/sec，RTX Spark 上 150+ tokens/sec，号称比同类模型快至 2 倍，4 个月内从零构建，开放权重已上架 Hugging Face。Thomas Wolf 转发并点评称，该模型把通常建议保持高精度的 lm_head 量化到 4bit 且只比 bf16 低 0.7 个百分点，结果令人印象深刻。
正文 · 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 !
Introducing Flint, @Recursive_SI’s first model: a fast local coding model built with our automated research system, the Eureka Machine. • Best-in-class fast local coding • Up to 2x faster than comparable models: 125+ tokens/sec on a MacBook Pro, 150+ on RTX Spark • Built from scratch in under 4 months Private, unmetered intelligence on your own machine. Open weights available now on @huggingface, run it locally on your favorite framework or try it for free on @opencode or @pidotdev.在 X 查看被引用的帖子
来源：Thomas Wolf · x.com