MARS Encoder for Multi-Agent Response Selection
This model was trained using SentenceTransformers Cross-Encoder class and is the model used in the paper One Agent To Rule Them All: Towards Multi-agent Conversational AI.
Training Data
This model was trained on the BBAI dataset. The model will predict a score between 0 and 1 ranking the correctness of a response to a user question from a conversational agent.
Usage and Performance
Pre-trained models can be used like this:
from sentence_transformers import CrossEncoder
model = CrossEncoder('csclarke/MARS-Encoder')
scores = model.predict([('question 1', 'response 1'), ('question 1', 'response 2')])
The model will predict scores for the pairs ('question 1', 'response 1') and ('question 1', 'response 2').
You can use this model also without sentence_transformers and by just using Transformers AutoModel class
- Downloads last month
- 12
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.