Prompt Engineering using Llama-2 model

[@AlainFavre-n4k]

Very instructive and easy to follow

[@abutareqrony4513]

Great explanation bro. Thanks

[@dr_einsteinn]

is the code working on any app platform like streamlit?

[@brijeshtanwar4392]

This is really helpful video for us. Can you make a video explaining all the parameters in transformers.pipeline()…. Like repetition_penalty, beam_search, etc…. And does these vary for other open source LLMs like mistral 7b, 13b

[@taijingshen4503]

Do we need to request access from the repo owner for llama 2 7b chat hf used here?

[@GangJiang-n6n]

Cool!!!

[@Abhishekkumar-wn9do]

if we off the internet still model will be downloaded using cache files..???

[@ycopie1126]

Only first time internet is needed to download the model. Next time onwards it will take from your local cache without internet.