RAG using Llama2 7b model

[saivineethabvns]

In 05_dataloader.ipynb in examples folder https://github.com/NVIDIA/GenerativeAIExamples/blob/v0.4.0/notebooks/05_dataloader.ipynb
is there a way to use Llama2 7b model instead of default Llama2 13b model

[shubhadeepd]

Hey @saivineethabvns, yes this is possible!

As a prerequisite step to run this notebook, you need to deploy this example following the steps here
https://nvidia.github.io/GenerativeAIExamples/latest/local-gpu.html#using-local-gpus-for-a-q-a-chatbot

Now in this step where you download the model https://nvidia.github.io/GenerativeAIExamples/latest/local-gpu.html#download-the-llama-2-model-and-weights , just download the llama-7b checkpoint instead of llama13b and you should be good to go.

Let me know if you face issues.

[rrpatil-1]

https://nvidia.github.io/GenerativeAIExamples/latest/local-gpu.html#using-local-gpus-for-a-q-a-chatbot
@shubhadeepd this link is not working now 404 error, does address moved. Can you share the newurl for same local gpu deployment