从ChatGPT到开源模型：我的AI探索之路

AI 摘要

一位作者在 Hugging Face 博客中回顾自己从使用 ChatGPT 转向开源模型 DeepSeek 和 Qwen 的经历，并分享了自己尝试训练超小模型（如 Single Floppy、floppyx3、floppyx4）的失败过程。作者认为开源模型可检查内部机制，比闭源服务更可信，并提到因图书馆屏蔽 DeepSeek 而短暂使用 Claude，但受限于速率限制。

正文节选

There's always a chance someone could be lying about a service if you can't prove it yourself. Tools like ChatGPT can claim security and privacy. Sure, you could put trust into the company, but you never know what you're buying. With open-source models like Qwen and DeepSeek, you can inspect what's happening behind the scenes. My first appreiation for open-source probably came with ny Raspberry Pi. Raspberry Pi OS (formerly known as Raspbian, and I wish it still was) is almost fully open. When I

发布时间：—

抓取时间：2026-09-14 01:12

来源机构：Hugging Face