Y
Hacker News
new
|
ask
|
show
|
jobs
by
sinuhe69
581 days ago
The demo they showed was full of repeated sentences. The 3B model looks quite dense, TBH. Did they just want to show the speed?
1 comments
newswasboring
580 days ago
3B models, especially in quantized state, almost always behave like this.
link