Andy (@viewerisland) 's Twitter Profile
Andy

@viewerisland

Building Gulp (YC W25)

ID: 2557375100

linkhttp://baiqinglyu.com calendar_today09-06-2014 19:12:15

225 Tweet

158 Takipçi

93 Takip Edilen

Andy (@viewerisland) 's Twitter Profile Photo
Andy
@viewerisland

4 months ago

For people that have tried post training the MiMo RL models, have anyone noticed that this model is *incredibly* verbose? Even for simple tasks it will go on for 20k+ tokens before an answer.