issues
search
nerdslab-club
/
cl_model
All models required for curious learner
GNU Affero General Public License v3.0
1
stars
0
forks
source link
Draw a detailed architectural picture for the pre-trainer model
#7
Closed
afmjoaa
closed
12 months ago
afmjoaa
commented
1 year ago
[x] Category probability cascading router
[x] Draw and name all three routers
[x] If the token is a function token, then use IFE and cross-attention
afmjoaa
commented
12 months ago
Done