I’m interested in trying out Nemo for Question Answering, as well as summarization .
I came across an excellent talk from GTC Fall 2022 (by Nirmalya De),
Enabling Fast-path to Large-Language-Model Based AI applications
In this talk, p-tuning is explained as the technique to customize LLMs for specific use-cases.
Considering that this is from 6 months ago, I wonder if this is still the recommended approach, or if it has been superseded by something else.
How can I try this out? I applied for Early acess on the Nemo page 3-4 days ago, but haven’t heard back yet.