silent chen's picture

8

silent chen

hackersilentchen

AI & ML interests

None yet

Organizations

None yet

hackersilentchen's activity

New activity in mingdali/ChatTruth-7B 9 months ago

请问会考虑拆分为1G左右的小文件么？现在这样10G的大文件，用纯CPU跑太难受了，谢谢

#2 opened 9 months ago by

hackersilentchen

New activity in Tele-AI/telechat-7B 11 months ago

可以用CPU模式跑么……

#2 opened 11 months ago by

hackersilentchen

New activity in 01-ai/Yi-6B about 1 year ago

考虑把模型文件拆分一下不，照顾下部分开发者比较低配的硬件……

#8 opened about 1 year ago by

hackersilentchen

New activity in xverse/XVERSE-13B over 1 year ago

64G内存跑不动

#6 opened over 1 year ago by

New activity in Qwen/Qwen-7B-Chat over 1 year ago

Model outputs gibberish after assistant response

#26 opened over 1 year ago by

New activity in xverse/XVERSE-13B over 1 year ago

才刚刚跑完QWEN-7B-CHAT，来打卡，对比看看

#2 opened over 1 year ago by

hackersilentchen

New activity in Qwen/Qwen-7B-Chat over 1 year ago

关于text-generation-webui调用

#4 opened over 1 year ago by

hackersilentchen

貌似很拉跨，一个7B的模型3090显存都不够载入，要是不安装它推荐的加速包，速度慢的像狗。

#12 opened over 1 year ago by

关于text-generation-webui调用

#4 opened over 1 year ago by

hackersilentchen

关于text-generation-webui调用

#4 opened over 1 year ago by

hackersilentchen