3.8B模型,998美元,跑到了CORE 0.384,真能这么干?
原创
大模型真的必须花巨资才能练出来吗?Hugo Vergnes做了个反例:一个人,花不到一千美金,把3.8B参数的小模型训练到CORE 0.384分。这个分数离前沿大模型还差得远,但对小模型来说已足够用。我不是说它有多强,只是觉得这路子值得看一眼。Hacker News上暂时没多少人讨论,我倒觉得这恰恰说明:小模型只要肯下功夫,也能打到能用的分数。对预算紧的团队来说,这条路径也许比追前沿更有意义。
原文:Training a 3.8B LLM to 0.384 CORE for $998 – Hugo Vergnes · 来源:Hacker News
版权声明
所有资源都来源于爬虫采集,如有侵权请联系我们,我们将立即删除
相关文章
- Stabyourself.net Games
- 【IT 早报】2026年11月19日 - 本周要闻与趋势
- 从均匀平铺到自适应路由:RINs 如何让扩散生成提速 10 倍?
- Claude Code makes a finished subagent send its report twice (70-second repro)
- Becerra faces a $2B budget deficit as potential AI bust looms
- Show HN: Agent Hive – cute Grokbot like agentic teams with queen and many bees
- Show HN: Lazycow Studio – turns footage you never edited into reels, locally
- Experiments in Weight-Space Programming
- Lindy Effect
- Meet Your Neighbors – A new type of political compass
最新文章
- Stabyourself.net Games 34分钟前
- 【IT 早报】2026年11月19日 - 本周要闻与趋势 37分钟前
- 从均匀平铺到自适应路由:RINs 如何让扩散生成提速 10 倍? 1小时前
- Claude Code makes a finished subagent send its report twice (70-second repro) 1小时前
- Becerra faces a $2B budget deficit as potential AI bust looms 2小时前
- Show HN: Agent Hive – cute Grokbot like agentic teams with queen and many bees 2小时前
- Show HN: Lazycow Studio – turns footage you never edited into reels, locally 2小时前
- Experiments in Weight-Space Programming 3小时前
- Lindy Effect 3小时前
- Meet Your Neighbors – A new type of political compass 4小时前
itfan123





