Opensource release for Predicting LLM Reasoning Performance with Small Proxy Model
AI & ML interests
None defined yet.
Recent Activity
Organization Card
We’re making Foundation Models.
models
22
trillionlabs/gWorld-8B
Image-Text-to-Text
•
9B
•
Updated
•
341
•
41
trillionlabs/gWorld-32B
Image-Text-to-Text
•
33B
•
Updated
•
261
•
23
trillionlabs/Trida-7B
Text Generation
•
8B
•
Updated
•
1.36k
•
9
trillionlabs/Trida-7B-Preview
Text Generation
•
8B
•
Updated
•
21
•
2
trillionlabs/Tri-70B-preview-SFT
Text Generation
•
70B
•
Updated
•
68
•
43
trillionlabs/Tri-21B
Text Generation
•
21B
•
Updated
•
5.35k
•
41
trillionlabs/Tri-7B-Intermediate-Checkpoints
Updated
•
17
•
6
trillionlabs/Tri-70B-Intermediate-Checkpoints
Updated
•
25
•
53
trillionlabs/1.9B-Intermediate-Checkpoints
Updated
•
10
•
3
trillionlabs/0.5B-Intermediate-Checkpoints
Updated
•
164
•
5