Model assets for the first Mixture-of-Lora technique applied to Llama. https://bit.ly/48bqshl
ceph
crumb
AI & ML interests
small models
Organizations
Collections
5
models
149
crumb/d87b8c-6h-128d
Text Generation
•
Updated
•
5
crumb/d3747f-12h-64d
Text Generation
•
Updated
•
11
crumb/ce7cf9-8h-96d
Text Generation
•
Updated
•
5
crumb/d38a14-32h-16d
Text Generation
•
Updated
•
23
crumb/3291e9-16h-32d
Text Generation
•
Updated
•
5
crumb/f358a4-8h-64d
Text Generation
•
Updated
•
11
crumb/efa25a-4h-128d
Text Generation
•
Updated
•
5
crumb/7457fb-2h-256d
Text Generation
•
Updated
•
7
crumb/GLORT2
Text Generation
•
Updated
•
35
crumb/160m-plus-sauce
Text Generation
•
Updated
•
10
datasets
51
crumb/onebench
Viewer
•
Updated
•
7.52k
•
39
crumb/askmistral-pile-2-15
Viewer
•
Updated
•
2.34M
•
130
•
7
crumb/songbird
Viewer
•
Updated
•
12M
•
35
crumb/semantic-corruption-t5-v1_1-small
Viewer
•
Updated
•
2.28k
•
35
crumb/semantic-corruption-t5-v1_1-base
Viewer
•
Updated
•
1.54k
•
37
crumb/semantic-corruption-t5-v1_1-large
Viewer
•
Updated
•
753
•
39
crumb/reup-test
Viewer
•
Updated
•
2k
•
5
crumb/redbeam-c4-rated-vit-l14-laion
Updated
•
31
crumb/dummy-cot-sampling-dataset-clean-preview
Updated
•
33
crumb/dummy-cot-sampling-dataset
Updated
•
34