Kimi K2.5 的确不错但好像训练的数据有点老?

查看 16|回复 1
作者:gap   
正准备开个会员,结果 opencode 可以限时免费用了,赶紧试了试,对项目问题的分析很到位,但怎么推理用的数据那么旧?
Let me search for more specific information about libmedia and iOS Safari limitations.
◈ Exa Web Search "libmedia AVTranscoder iOS Safari performance file size limitations WASM 2024"
◈ Exa Web Search "iPhone Safari file upload size limit blob memory WebAssembly"
Thinking: Based on the search results, I can now provide a comprehensive answer about Option 2 (libmedia/AVTranscoder) and its viability on iPhone Safari:
Key findings:
1. iOS Safari WASM Memory Issues:
   - There's a history of Out-Of-Memory (OOM) errors on iOS when using WASM (GitHub issue from 2022 shows "Unhandled Promise Rejection: RangeError: Out of Memory" on iOS 15.2)
   - ffmpeg.wasm has a 2GB file size limit (GitHub issue #623)
   - Safari WASM was limited to 2GB until 2021, now supports up to 4GB but with memory fragmentation issues

数据, Safari, wasm

vacuitym   
一般都是用旧的数据集训练的,感觉国内的和国外的模型还是有差距,你可以试试: https://chat.vacuity.me/#/
您需要登录后才可以回帖 登录 | 立即注册

返回顶部