You can try deploying our models using our packaged solution (with vLLM), you'll get an API with control on temperature (which is how you get rid of repetition)
Deploying AI Models with vLLM and Temperature Control
By
–
By
–
You can try deploying our models using our packaged solution (with vLLM), you'll get an API with control on temperature (which is how you get rid of repetition)