Love your tutorials, keep them coming 🙂

Thanks. I'd love to see how to fine-tune one of the LLaMa 2 Pretrained models via Colab if that were possible or Pytorch.

Thanks for making the video. 🎉

AMAZING! Thank you so much!

Now that it is open source, is it easier to embed Pdf and fine-tune the model to work with those ? Or another ai would be better suited ?

Very helpful. Thank you

Thanks for sharing!. What is the best way to prepare dataset for tabular question answer?

thank you so much ! could you possibly make a tutorial to show how we can train LLaMa on our own data?

Thanks alot, can I use LLAMA model using my own PDF files and Langchain, to build a qustion answering system ? the same way as using openai models ?

Thank you for posting this video. Hope you could share LangChain implementation of LLaMa 2

Thx for your video, can you make a tutorial to explain how to train Llama 2 on your own custom dataset?

Getting this error "'LlamaTokenizer' object has no attribute 'sp_model'", can anyone fix this

You are doing God's work. Of course by God I mean our future AI overlord.

Is there anybody who got Llama working on Windows? I tried to use the ipynb file and ran it with the Linux subsystem, but got lots of errors. Before that, I also tried following the official meta instructions from GitHub, but didn't get further than downloading the model and setting up the Conda environment with torch/cuda and running the installation script. Like, what do I do next? The Meta GitHub instructions are not particularly straightforward on how to use it 😅

Any suggestion on how to use the private data embeddings with lama2?

Hello, could you make a video about the cheapest server providers that supports running this? I keep running out of ram.

How do I use the non-chat version/the base model? The restrictions on the chat version are really annoying. Thanks.

To run locally (on Linux): Download the Colab as ipynb this is not enough for running.... please explain more, what about content folder?

What about the "training" tab that you didn't explain?

will this collab notebook won't work on windows device servers

how to set up this on my local system. I have GPU.

what GPU do i need for largest llm model of Llama 2 to work with ? is 16GB enough ? i have RTX 3070 , i am looking to get intel's ARC A770 very informative video., thank you.

Hey thanks for the tutorial. I really love your content bro. But what if I want to add an API to this Llama2 collab. Like I want an API endpoint that is connected with Llama2 collab so that whenever I hit that endpoint it should give me the response from it. Will be waiting for your reply. Lot’s of love buddy ❤

How to invoke the deployed model prorgammatically?

Is there anyway I could turn this free notebook into a api I could programmatically query?

how open de program of llama2? how do you can forget this

Can you make a video on how to use Llama 2 through code just like how we use GPT models in code?

Hi , can you please create a video of chatpdf like system using llama2 open source model

I love open source.

ungakuda LinkedIn la eppadi connect panurathu solluga?

how to run 70B on windows?

*HOW TO DOWNLOAD THE WHOLE MODEL TO HAVE IT ON MY PC LOCALLY **#WITHOUT** INTERNET? YOU NEED TO EXPLAIN THAT*

Make video on fine tuning and deploy to hugging face please

*You said use it commercially ? how? any ideas?* 1:12

Doesn't work anymore.

Hello, I am getting an error "ImportError: cannot import name 'is_npu_available' from 'accelerate.utils' (/usr/local/lib/python3.10/dist-packages/accelerate/utils/__init__.py)" can you please help me how can i fix this?