Build a Chatbot with Llama 3 8B & 70B + Ollama + Streamlit
Vložit
- čas přidán 29. 08. 2024
- Today, I'll show you how to build a llm app with the Meta local Llama 3 model, Ollama and Streamlit for free using LangChain and Python. Happy learning!
▶ Subscribe: bit.ly/subscri...
▶ Join my channel: bit.ly/join-ti...
00:01 Introduction
01:10 Setup
02:38 Initialize Llama 3 with Ollama
05:55 Build chatbot with Streamlit
08:00 Inference
09:03 Test Llama 3 70B
RELATED VIDEOS:
▶ LangChain Tutorials: bit.ly/langcha...
▶ Generative AI for DS: bit.ly/genai-f...
▶ HuggingFace Tutorials: bit.ly/hugging...
▶ Generative AI Tutorials: bit.ly/generat...
▶ LLMs Tutorials: bit.ly/llm-tut...
FOLLOW ME:
▶ Medium: / tirendazacademy
▶ X: / tirendazacademy
▶ LinkedIn: / tirendaz-academy
Project Files: github.com/Tir...
Hi, I am Tirendaz, PhD. I create content on generative AI & data science. My goal is to make the latest technologies understandable for everyone. Don't forget to subscribe and turn on notifications so you don't miss the latest videos.
#ai #generativeai #langchain
Just finished the tutorial and some other on your channel! How do I make a chatlike interface on streamlit where answers from the llm is displayed and remembered for further conversation?
Cool. When are you going to make a video about PDF queries ? That would be great!
Hi any steps you can suggest i should learn first?
I'm from game development background with c#, I know a little bit of python.
I don't know about conda or anything else
Hi, the inference speed of Ollama in your system is impressive. What is your system setup ?
Hi, thanks for your feedback. I have an 4070 Ti Super with 16gb VRAM graphics card and 64gb Ram.
This is the main issue of llama3. It's necessary a huge computer.
awesome
Hi, Thanks to the video. I followed all the instructions and I make an adjustments but when I type this prompt "create a countplot of color"
The output response is:
"Unfortunately, I was not able to answer your question, because of the following error:
[Errno 2] No such file or directory: 'D:/Workspace_vs_code/Chatbot/exports/charts/temp_chart.png'
"
How to solve this? thank you
Very cool!
But this cannot be done in a deployed streamlit app for anyone to use... right?
why i am getting:
llm = ollama(model="llama3")
TypeError: 'module' object is not callable
ollama (O) is capital.
What is the min system requirements to build this app locally ?
8Gb Ram
For Llama-3 70B, you need at least 40 GB RAM.
@@TirendazAI Can a relatively less powerful laptop with 16 GB of RAM can built any Llama-3 models? For instance, could it run the Llama 3-8B model or any other model available in huggingface ?
Egitimleriniz neden ingilizce
Yapay zeka geliştiricilerinin ortak dili ingilizce
and I would not have been able to subscribe if you didn't work in English 😅.
I appreciate this tutorial.
@@robkennedy5906 Glad to hear that 😀