Improve ROSA customer experience (and customer retention) by leveraging foundation models to do “gpt-chat” style search of Red Hat customer documentation assets.
Other
24
stars
11
forks
source link
Deploy Language Model(s) to our cluster exposing a completion API #27
This should be an enabler for #25 and #26, but also will help to explore open language models and how to serve them.
Goal: to deploy one or more of the publicly available Language Models to our cluster, so that they can be accessed via an API hosted by ourselves.
A comprehensive list of such models can be found in Hugging Face's Transformers' list of models, e.g. https://huggingface.co/docs/transformers/model_doc/bloom (see the list of text models). A summary / classification is also available here: https://huggingface.co/docs/transformers/model_summary#summary-of-the-models