schonsense/llargema_405b_157b_heal_v1
157B
•
Updated
Mark Fenlon PRO
schonsense
AI & ML interests
Testing ground repo for merging, finetuning, and LORA manipulations.
Recent Activity
updated
a model
about 20 hours ago
schonsense/llargema_405b_157b_heal_v1
published
a model
about 22 hours ago
schonsense/llargema_405b_157b_heal_v1
updated
a model
5 days ago
schonsense/slim405B_Inst
Organizations
updated
a
model
about 20 hours ago
published
a
model
about 22 hours ago
updated
a
model
5 days ago
liked
a
dataset
9 days ago
Eval request
#521 opened 10 days ago
by
schonsense
updated
a
model
about 1 month ago
published
a
model
about 1 month ago
updated
3
models
about 1 month ago
published
a
model
about 1 month ago
updated
a
model
about 1 month ago
published
a
model
about 1 month ago
commented on
The Optimal Architecture for Small Language Models
about 1 month ago
Very interesting, thank you.
commented on
The Optimal Architecture for Small Language Models
about 1 month ago
Interesting. If you compare only the model layer parameters to their performances, are any different trends seen? Thank you for responding.
commented on
The Optimal Architecture for Small Language Models
about 1 month ago
Can you discuss the additional things contributing to param count that were not mentioned in your article? embedding/head size, intermediate dimensions? I'm struggling to see how a 768x4 has equivalent params to a 512x12.
published
a
model
about 1 month ago
updated
3
models
about 1 month ago