Creating CHAT GPT Clone in node js and react js using LLAMA 2

preview_player
Показать описание
Let's try to build a chat gpt clone using LLAMA 2
Рекомендации по теме
Комментарии
Автор

Thanks a million bro, it was much needed someone needs to break the capistalistic ideology of evil openai company

Birkullanci
Автор

That frustration when you misunderstood type 😂😂

Bcs-Mohtisham
Автор

Nice tutorial! What is your system specs to run this locally?

Bcs-Mohtisham
Автор

hey can i get link to this repo? followed te tutorial step by step but now stuck at the part where we are establishing connnection between front end and backend.
Even tho backend is running fine and showing that model is running and showing the message that there is a new connection, in front end console is not showing that "vite is connected" also getting no response from the model wheni send the mesage :(

siddy
Автор

How to deploy the backend, because with the model the size would be too large ?

Thedeentour
Автор

hey, good tutorial, just want to confirm if you ran lllama locally if yes, will there be a gpu needed for it or you can run it without it?

siddy
Автор

how to host backend?? cz as you know the model is around 4 gb so github not allow to upload it what should i do bro???
i'm using turbo repo

aritradaschowdhury
Автор

Bro, how to make a software and how to deploy them, please one video on this topic

rahulkharola
Автор

how to download model. facing issue kindly make one video for download modal from scratch. I dont have python in my system then how I could download that model.

fahadhassan
Автор

Hey bro I'm running into issues with CORS would you be so kind to help me out?

Gexway
Автор

how we can fine tune the model and use it?

ranaayushmansingh
Автор

Hello . I‘m requesting it from Korea after watching the video. I want to make a chatbot for our customers by fine tuning it with the dataset I want with the LLAMA3 model. Is it possible? Please let me know how much it will cost.

jlive
Автор

Can i get code and can you also help to train my own data on llama2?

muhammadmuzammil