正在加载视频...

视频加载失败

I was able to run Meta’s Llama 2 7B parameters locally without internet connection on my 15 Pro Max It was a bit hot and a dumb cuz small LLM as a beta app (LLM Farm) Imagine it was a iOS centric and optimized one for Apple uses tho 🤌🏻

17,614 次观看 • 2 年前 •via X (Twitter)

8 条评论

AppleLeaker 的头像
AppleLeaker2 年前

Wow. Could you please share how you were able to run this on-device?

ShrimpApplePro 🍤 ずっと真夜中でいいのに 的头像
ShrimpApplePro 🍤 ずっと真夜中でいいのに2 年前

LLM Farm (Testflight) You can use the sample models or trying others on hugginface I think you can get a GPT 2 as well I would recommend run it on a M1 machine or A17 Pro cuz holy hell it eats RAM and hot af on first run 💀

ShrimpApplePro 🍤 ずっと真夜中でいいのに 的头像
ShrimpApplePro 🍤 ずっと真夜中でいいのに2 年前

Idk if it tuned after I talked to it but its responds are a lot faster than 2 days ago.

anpaure 的头像
anpaure2 年前

respect for zutomayo

Ben 的头像
Ben2 年前

How much memory does this 7b model take?

La Pyae 🚀 的头像
La Pyae 🚀2 年前

I wonder if it is still work for Llama 3.1 as well .

INIYSA 的头像
INIYSA2 年前

To add, iPhone autocorrect feature already using smal gpt-2 based model

ShrimpApplePro 🍤 ずっと真夜中でいいのに 的头像
ShrimpApplePro 🍤 ずっと真夜中でいいのに2 年前

Ooh interesting

相关视频