วีดีโอ

I am also waiting

Great! Awaiting for the next videos. Thanks for your efforts.

thanks bro, really helpfull video

nice explanatation

Your video is very good.. easy to learn the concept easily..thank you sir..Please provided the detailed example for grammar based LM

Very nice 👍

hi with a 16GB RAM i am not able, to save embedding in the collection what could be the issue?What are your system configuration, my kernel is crashing

can i usethis in vscode?

Really great explanation..... But i am stuck in a problem of getting space on gpu. If i tried this on google collab ,the free version gets collapsed due to all memory usage. Pls suggest me for this solution or list the name of small models that are under 12gb of space & are used for prompting purpose.

Thanks for your time... Please may I ask how to download coda toolkit on my laptop to support GPU support. The code for Coda or cpu is not working on my laptop

is the code working on any app platform like streamlit?

I currently have the problem that it only says "Loading widget..." when I try to run the code and doesn't display the progress bar. Do you possibly know how to fix this?

System Configuration used?

Thanks! this was my first AI development video watch.

@3:58 Fine-tuning of a LLM is done via such chat or instructions

nlp concepts you are the best to explain super bro

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

Great video. Thank you ycopie!

hi. thank you for this video. i am new to this field. i wanna ask where is the model located? i have downloaded llama 2 70B from meta. i got it after signing up and from a link they have provided through mail. if you are working in llama-2 i think you might know what i am talking about. i am new here so i am confused. what model can i used to work on my local system .

what will we do if i need interactive mode, like having conversation like we do with chatgpt

really subtle! subscribed

love your username lol

bro just found your vedio for this topic and you teched the best all others are just shit bro thanks a lot if you see this message

Very instructive and easy to follow

how to fine tune with our own data sets, like answer the pdf of our own data sets.

i'm new to LLM and i just wanted to know that you need all these access for using llama, but when you'd use ollama you just put "ollama run llama2" in the terminal, so whats the difference? they can access it without any explicit access from meta??

Great explanation bro. Thanks

Great video, and it is indeed the right translation to french :)

Thank you for this hands-on! Initially I tried it on my laptop which although has an NVDA GEFORCE GTX, it can't run very well. Eventually I have to run it on Colab (T4 GPU), though not with adding the following lines to help with the GPU usage (just sharing) : !pip install accelerate from accelerate import Accelerator accelerator = Accelerator() device = accelerator.device

ValueError: You are trying to offload the whole model to the disk. Please use the `disk_offload` function instead. i got this error

You just got a new subscriber. Good job with the explanations.

Langchain in related to RAG ? I am very new.

Very helpful. Thanks a lot for this.

Hi Yash. I have been trying to run your code on Colab. I have been facing issues while running model = AutoModelForCausalLM.from_pretrained( "meta-llama/Llama-2-7b-chat-hf", device_map='auto' ) I tried passing access token, but getting errors. Your guidance would be greatly appreciated

Do you offer any paid consulting? I’m stuck on an installation error.

Thanks for this discussion !

ConnectionError: ('Connection aborted.', ConnectionResetError(10054, 'An existing connection was forcibly closed by the remote host', None, 10054, None)) bro iam getting this error when running on jupyter notebook. please help.

ConnectionError: ('Connection aborted.', ConnectionResetError(10054, 'An existing connection was forcibly closed by the remote host', None, 10054, None)) bro iam getting this error when running on jupyter notebook. please help.

How are you loading a 7b model locally? can I know your RAM

thank you 🙏

thank you for sharing your knowledge its very helpful

good job!

good vid

hf represents human feedback not hugging face

very good and simple

The model takes lot of time to respond , like 3minutes for 50 tokens. Any suggestions to how we can improve the timing, would be much appreciated. I am running it on V100 on Databricks. Enough Compute and memory is present.

24:39 - Fun part of the video, good luck Yash ! Thanks for the video.

nice tutorial but how would you do to wait for the prompt.. so we can enter the prompt like what is capital in Indisa and press enter.. then the model should reply.. how to do it.

Please share you system specs, specially about GPU you are using

Can you please tell me your PC specs ?