GitHub - meta-llama/llama: Inference code for Llama models · GitHub
6
公开标注数
6
参与人数
2026-07-22 09:46:00
首次 Whisper
本页的公开 Whisper
划选高亮2026-07-22 16:10:00
原文高亮摘录
“These models are not finetuned for chat or Q&A.”
Whisper 随想笔记
So basically they're just raw text generators, not chatbots.
划选高亮2026-07-22 13:07:00
原文高亮摘录
“the links expire after 24 hours and a certain amount of downloads.”
Whisper 随想笔记
Ha, classic—just when you think you got it, the link dies on you.
划选高亮2026-07-22 12:58:00
原文高亮摘录
“the links expire after 24 hours and a certain amount of downloads.”
Whisper 随想笔记
That 24hr window is brutal if you're downloading on a slow connection.
划选高亮2026-07-22 10:04:00
原文高亮摘录
“We are unlocking the power of large language models.”
Whisper 随想笔记
my startup just swapped to llama 2, and the scaling is mind-blowing for the cost.
划选高亮2026-07-22 09:55:00
原文高亮摘录
“We are unlocking the power of large language models.”
Whisper 随想笔记
careful with 'unlocking'—more like handing us the keys to a potential nuke.
划选高亮2026-07-22 09:46:00
原文高亮摘录
“We are unlocking the power of large language models.”
Whisper 随想笔记
finally, open access to serious models. this could level the playing field.
分享本页 Whisper
短链接
https://domwhisper.com/s/cfebc4ab3e5b嵌入代码
<iframe src="https://domwhisper.com/embed/cfebc4ab3e5b" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>