UniRef50 is built by clustering UniRef90 seed sequences that have at least 50% sequence identity to, and 80% overlap with, the longest sequence in the
🔄 In a Training Loop
khairi abidi
khairi
AI & ML interests
Language Modeling, Protein Language Modeling, Protein Annotation
Recent Activity
updated a model 5 days ago
khairi/barca-0.8b-base published a model 5 days ago
khairi/barca-0.8b-base liked a Space 21 days ago
khairi/KCNG-ExplorerOrganizations
datasets 25
khairi/kothar-dataset-it
Viewer • Updated • 2.63M • 202 • 1
khairi/kothar-pretrain-mix-v1
Viewer • Updated • 950k • 23
khairi/uniref50-replay-mix-v1
Viewer • Updated • 10.7M • 99
khairi/uniref50-10
Viewer • Updated • 3M • 27
khairi/uniref50-9
Viewer • Updated • 2.68M • 11
khairi/uniref50-8
Viewer • Updated • 3.4M • 10
khairi/uniref50-7
Viewer • Updated • 3.86M • 10
khairi/uniref50-6
Viewer • Updated • 14.3M • 11
khairi/uniref50-5
Viewer • Updated • 9.44M • 10
khairi/uniref50-4
Viewer • Updated • 7.37M • 13