This collection contains held-out splits for testing Flow-Judge-v0.1.
Flow AI
Enterprise
company
Verified
AI & ML interests
LLM system evaluation, Automatic LM improvements
Organization Card
Flow AI is the system for evaluating and improving your LLM application.
spaces
1
models
7
flowaicom/Flow-Judge-v0.1-W8A16
Updated
•
21
•
1
flowaicom/Flow-Judge-v0.1-W4A16
Updated
•
37
•
1
flowaicom/Flow-Judge-v0.1-FP8
Updated
•
56
•
1
flowaicom/Flow-Judge-v0.1-AWQ
Text Generation
•
Updated
•
4.31k
•
5
flowaicom/Flow-Judge-v0.1
Text Generation
•
Updated
•
1.26k
•
43
flowaicom/Flow-Judge-v0.1-Llamafile
Updated
•
285
•
1
flowaicom/Flow-Judge-v0.1-GGUF
Text Generation
•
Updated
•
110
•
7
datasets
9
flowaicom/legalbench_contracts_qa_subset
Viewer
•
Updated
•
100
•
41
flowaicom/Flow-Judge-v0.1-3-likert-heldout
Viewer
•
Updated
•
300
•
33
flowaicom/Flow-Judge-v0.1-5-likert-heldout
Viewer
•
Updated
•
274
•
36
flowaicom/Flow-Judge-v0.1-binary-heldout
Viewer
•
Updated
•
316
•
37
flowaicom/RAGTruth_test
Viewer
•
Updated
•
2.7k
•
48
flowaicom/covid_qa
Viewer
•
Updated
•
1k
•
43
flowaicom/PubMedQA
Viewer
•
Updated
•
1k
•
39
flowaicom/HaluEval
Viewer
•
Updated
•
10k
•
38
flowaicom/Feedback-Bench
Viewer
•
Updated
•
1k
•
42