Our growing collection of task specific LLM as a Judge adapters for performing evaluations
GroundedAI
company
AI & ML interests
As part of our mission to foster grounded generative AI applications, we have trained and released SLMs tailored to model based evaluation. Our open source models aim to provide efficient, high-performing alternatives to black box LLMs currently used for evaluating GAI apps, ensuring outputs remain grounded in factual information and ethical principles.
Recent Activity
View all activity
Organization Card
GroundedAI
Mission
At GroundedAI, we are committed to fostering the responsible development of grounded generative AI (GAI) applications. Our mission is to push the boundaries of GAI while ensuring it remains grounded in factual information and ethical principles.
Collections
2
Base model(s) merged with the specific evaluation task adapter. Each model performs excellently for its purpose and remains useful for general tasks.
-
grounded-ai/phi3-toxicity-judge-merge
Text Generation • Updated • 18 -
grounded-ai/phi3-rag-relevance-judge-merge
Text Generation • Updated • 21 -
grounded-ai/phi3-hallucination-judge-merge
Text Generation • Updated • 21 -
grounded-ai/phi3.5-hallucination-judge-merge
Text Generation • Updated • 72 • 1
models
10
grounded-ai/phi3.5-rag-relevance-judge
Updated
•
7
grounded-ai/phi3.5-rag-relevance-judge-merge
Text Generation
•
Updated
•
9
grounded-ai/phi3.5-hallucination-judge-merge
Text Generation
•
Updated
•
72
•
1
grounded-ai/phi3-rag-relevance-judge-merge
Text Generation
•
Updated
•
21
grounded-ai/phi3-toxicity-judge-merge
Text Generation
•
Updated
•
18
grounded-ai/phi3-hallucination-judge-merge
Text Generation
•
Updated
•
21
grounded-ai/phi3.5-hallucination-judge
Updated
•
175
•
3
grounded-ai/phi3-hallucination-judge
Updated
•
10
•
2
grounded-ai/phi3-rag-relevance-judge
Updated
•
2
•
2
grounded-ai/phi3-toxicity-judge
Updated
•
3