🐙 Lunch & Learn: Intro to Open Source Models
ฝัง
- เผยแพร่เมื่อ 8 มี.ค. 2024
- ----------------------------------------------------
🤖 Sign up here to get accompanying workbooks, summaries, and notifs for future lunch & learns: www.lonelyoctopus.com/email-s...
✉️ NEWSLETTER: tinahuang.substack.com/
It's about learning, coding, and generally how to get your sh*t together c:
🐙 Lonely Octopus: www.lonelyoctopus.com/
Check it out if you're interested in learning AI & data skill, then applying them to real company projects!
🔗Affiliates
========================
My SQL for data science interviews course (10 full interviews):
365datascience.com/learn-sql-...
365datascience.pxf.io/WD0za3 (link for 57% discount for their complete data science training)
Check out StrataScratch for data science interview prep:
stratascratch.com/?via=tina
🎥 My filming setup
========================
📷 camera: amzn.to/3LHbi7N
🎤 mic: amzn.to/3LqoFJb
🔭 tripod: amzn.to/3DkjGHe
💡 lights: amzn.to/3LmOhqk
📲Socials
========================
instagram: / hellotinah
linkedin: / tinaw-h
discord: / discord
🤯Study with Tina
========================
Study with Tina channel:
/ @studywithtina7726
How to make a studying scoreboard:
• The scoreboard I use t...
Scoreboard website:
scoreboardswithtina.com
livestreaming google calendar:
bit.ly/3wvPzHB
🎥Other videos you might be interested in
========================
How I consistently study with a full time job:
• How I consistently stu...
How I would learn to code (if I could start over):
• How I would learn to c...
🐈⬛🐈⬛About me
========================
Hi, my name is Tina and I'm an ex-Meta data scientist turned internet person!
📧Contact
========================
youtube: youtube comments are by far the best way to get a response from me!
linkedin: / tinaw-h
email for business inquiries only: hellotinah@gmail.com
========================
Some links are affiliate links and I may receive a small portion of sales price at no cost to you. I really appreciate your support in helping improve this channel! :)
![[1hr Talk] Intro to Large Language Models](http://i.ytimg.com/vi/zjkBMFhNj_g/mqdefault.jpg)
Yess, let us know about RAG, fine tuning and Function calling next! Would love to know how to use these.
First time viewer. Thank you! I actually appreciated the chaos. It's enlightening to see how these things get troubleshooted (wait... is it troubleshot?) live instead of everything running perfectly.
Awesome work, you are very kind for sharing this information
Firstly, I want to know how long it will take me to fully learn about open source models and LLMs?
I have some knowledge in Python. Do I need to know Python completely to contribute to open source and LLM's?
Yes, prioritize the fundamentals
Yes, please explain the intricacies of RAG. I'm currenly looking into llama-index and i'd love to know how to optimize performance and load a ton of data from platforms like jira, confluence, git etc. Another great topic would be the costs associated with custom models (seems like it only pays off if the models are in heavy use, as the vpc instances are quite expensive per hour compared to pay-per-token FM endpoints).
You have plans to load your own data source and build your own lldm from llama-index? Love to know more.
@@baoshenyi yes, idea is to build one chat bot for the whole campany knowing everything. I m confident llama index is the tool for the job, but I'm still in the brainstorming phase, and only tried some basic information retrieval and build a small agent network with the react agent from the lib. I really like it, but RAG with so much data probably wont work out of the box without some optimizations like query finetuning etc.
@@Scarage21 Thnks for the reply. I am new to this area. I wonder what is RAG? do you build your company knowing base on pdf and wiki or other dara format? thanks again!
Ohhh. shit I missed the stream!
Oh nooo 🥺
Such a beautiful and smart young lady.
Tina is always looking confused at the beginning of every stream 😂