The TopicGPT model has been developed with the aim of detecting and extracting the primary subject matter of conversations. This capability can prove to be exceedingly useful in a wide range of natural language processing applications. To use the TopicGPT model, enter an input conversational text or data for analysis. Subsequently, the model processes the input and returns a reasonably accurate estimate of the topics of the conversation.
Additional Details
It is essential to note that the input provided to this model must commence with #CONTEXT# (BOS) and terminate with #TOPIC# (EOS). Here is an example:
#CONTEXT# The quick brown fox jumps over the lazy dog! #TOPIC#
- Downloads last month
- 190
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model authors have turned it off explicitly.