- 74
- 31 762
AI Tinkerers Ottawa
Приєднався 10 лип 2023
As a Language Model, I cannot help you with that.
Revolutionizing Learning with AI Powered Study Tools - Myroslav Vozniak
Revolutionizing Learning with AI Powered Study Tools - Myroslav Vozniak
Переглядів: 85
Відео
Tone Lenses Simulating Misunderstandings - Mauve
Переглядів 649 годин тому
Tone Lenses Simulating Misunderstandings - Mauve
Nomadic Infrastructure Design for AI Workloads - Xe Iaso
Переглядів 329 годин тому
Nomadic Infrastructure Design for AI Workloads - Xe Iaso
Instant MVP prototyping using lovable.dev - Chris Phillips
Переглядів 639 годин тому
Instant MVP prototyping using lovable.dev - Chris Phillips
Machine vision video applications with Roboflow workflows w/Sachin Agarwal (AI Tinkerers Ottawa)
Переглядів 1752 місяці тому
Machine vision video applications with Roboflow workflows w/Sachin Agarwal (AI Tinkerers Ottawa)
The ideal environment for agentic codegen w/ Harry Brundage @ Gadget (AI Tinkerers Ottawa)
Переглядів 1102 місяці тому
The ideal environment for agentic codegen w/ Harry Brundage @ Gadget (AI Tinkerers Ottawa)
LLMs in the User Agent w/ Mauve Signweaver (AI Tinkerers Ottawa)
Переглядів 1702 місяці тому
LLMs in the User Agent w/ Mauve Signweaver (AI Tinkerers Ottawa)
Interpretability w/ Alice Rigg (AI Tinkerers Ottawa)
Переглядів 2062 місяці тому
Interpretability w/ Alice Rigg (AI Tinkerers Ottawa)
Cerebras Systems world's fastest inference w/ Maria Mihu & Gleb Kazantaev (AI Tinkerers Ottawa)
Переглядів 2822 місяці тому
Cerebras Systems world's fastest inference w/ Maria Mihu & Gleb Kazantaev (AI Tinkerers Ottawa)
AI Tinkerers Ottawa: What's new in AI? 11/19/2024
Переглядів 442 місяці тому
greg is on vacation so this abomination took his place.
(AI Tinkerers Ottawa) Gemini models, agentic frameworks, and AI scene in Singapore w/ Sam Witteveen
Переглядів 782 місяці тому
Sam's channel: @samwitteveenai Sam's Patreon: www.patreon.com/samwitteveen
AI Tinkerers Ottawa: year 2 recap (2024)
Переглядів 3032 місяці тому
AI Tinkerers Ottawa: year 2 recap (2024)
(AI Tinkerers Ottawa) Enterprise LangGraph AI Agent w/ Brendon Geils @athenaintelligence
Переглядів 1033 місяці тому
www.linkedin.com/company/athena-intelligence-ai/
(AI Tinkerers Ottawa) Fine tuning Whisper with PEFT LORA w/ Rishab Bahal
Переглядів 6953 місяці тому
Explore the intricacies of fine-tuning OpenAI's Whisper speech-to-text model for tailored business and general use cases. Discover effective Parameter Efficient Fine Tuning techniques, including an insightful overview of LORA, to enhance your understanding and application of this powerful tool.
(AI Tinkerers Ottawa) Real-Time Stable Diffusion w/ Marco Tundo
Переглядів 3003 місяці тому
(AI Tinkerers Ottawa) Real-Time Stable Diffusion w/ Marco Tundo
(AI Tinkerers Ottawa) Formulaic w/ Gabriel Tech Lead @ Mozilla
Переглядів 773 місяці тому
(AI Tinkerers Ottawa) Formulaic w/ Gabriel Tech Lead @ Mozilla
(AI Tinkerers Ottawa) What's new in AI w/ Greg Meldrum 10/15/2024
Переглядів 653 місяці тому
(AI Tinkerers Ottawa) What's new in AI w/ Greg Meldrum 10/15/2024
(AI Tinkerers Ottawa) Web scraping for LLM with Firecrawl w/ Eric Ciarla
Переглядів 1723 місяці тому
(AI Tinkerers Ottawa) Web scraping for LLM with Firecrawl w/ Eric Ciarla
(AI Tinkerers Ottawa) YOLO and Computer Vision on Roboflow for AI Engineers w/ Emily Gavrilenko
Переглядів 3353 місяці тому
(AI Tinkerers Ottawa) YOLO and Computer Vision on Roboflow for AI Engineers w/ Emily Gavrilenko
(AI Tinkerers Ottawa) RAG Insights w/ Sebastian Witalec & Zain Hasan (Weaviate)
Переглядів 1254 місяці тому
(AI Tinkerers Ottawa) RAG Insights w/ Sebastian Witalec & Zain Hasan (Weaviate)
(AI Tinkerers Ottawa) Whats new in AI? /w Greg Meldrum September 2024
Переглядів 1104 місяці тому
(AI Tinkerers Ottawa) Whats new in AI? /w Greg Meldrum September 2024
(AI Tinkerers Ottawa) Opening 8/20/2024 w/ Jen Schellinck
Переглядів 574 місяці тому
(AI Tinkerers Ottawa) Opening 8/20/2024 w/ Jen Schellinck
(AI Tinkerers Ottawa) What's new in AI w/ Greg Meldrum (8/20/24)
Переглядів 604 місяці тому
(AI Tinkerers Ottawa) What's new in AI w/ Greg Meldrum (8/20/24)
(AI Tinkerers Ottawa) LLMs in Data Classification w/ Ghayath Janoudi (Loon Inc.)
Переглядів 2394 місяці тому
(AI Tinkerers Ottawa) LLMs in Data Classification w/ Ghayath Janoudi (Loon Inc.)
(AI Tinkerers Ottawa) Google Cloud, Gemini & Vertex Studio w/ Brett Tackaberry (Google)
Переглядів 614 місяці тому
(AI Tinkerers Ottawa) Google Cloud, Gemini & Vertex Studio w/ Brett Tackaberry (Google)
(AI Tinkerers Ottawa) Prompt Engineering from an ex-GitHub Copilot engineer w/ John Berryman
Переглядів 2634 місяці тому
(AI Tinkerers Ottawa) Prompt Engineering from an ex-GitHub Copilot engineer w/ John Berryman
(AI Tinkerers Ottawa) LLM Evals - Julia Neagu, CEO @Quotient AI / ex-GitHub Copilot Dir. of Data
Переглядів 2515 місяців тому
(AI Tinkerers Ottawa) LLM Evals - Julia Neagu, CEO @Quotient AI / ex-GitHub Copilot Dir. of Data
(AI Tinkerers Ottawa) What is co-hacking?
Переглядів 4955 місяців тому
(AI Tinkerers Ottawa) What is co-hacking?
(AI Tinkerers Ottawa) Local LLM, tool calling and image generation Discord bot - Marc Antoine Ruel
Переглядів 4055 місяців тому
(AI Tinkerers Ottawa) Local LLM, tool calling and image generation Discord bot - Marc Antoine Ruel
👏🏻👏🏻👏🏻
Good presentation. Will you be able to post your program?
You're a real one of you know about his real identity and you don't share it on Twitter and let bro stay mostly anon.
Deport
go to europe, white boi
So that’s why you really look like lol
😂 Humanity is doomed if this is the future 😂
great presentation!
At 15:18, the author says that Full Fine-Tuning is a subset of the LORA technique, when in reality, I believe, it should be the opposite. In full fine-tuning, all the parameters of the model are considered, whereas when doing LORA, it is a subset.
In Full fine tuning all parameters are trained. In LORA we train subset of parameters which is based on parameter r. When r increases number of trainable parameters also increases. But when not doing transfer learning, we end up choosing r so high that hypothetically we are training 100% of parameters which is equivalent to full fine tuning. That's why LORA only works well while transfer learning. Otherwise you will end up with r which will make you train all parameters (Full fine tuned). Hence Full fine tuning is a special case of LORA. I hope I was able to explain.
@ Hi Rishabh, Thanks for your response, I think now I understand, in LORA, the number of parameters being trained is directly proportional to the value of r. Hypothetically, if the value of r is too high, it will amount to 100% of trainable parameters which is called full fine tuning. So, all this said, Full Fine tuning becomes a special case of LORA where value of r is too high I believe now I understand, Thanks for your insights!
Fast forward few months and now he's making brazenly islamophobic comments on twitter. Sad developments
Kache 🎉🎉🎉🎉
Retroactively? 😉 Or should I come back in 2025?
I lowkey wanna send you one but you should come visit haha
Thanks Mauve! This was great, we definitely need more local options for people
Source Code please
This is amazing, why did I not hear about this before!! Will be there for the next event
AI Tinkerers Ottawa is great!
Epic video! Thanks for putting this together!!
What happened to her voice?
Do you have demo notebook or source code, thanks.
Great presentation, can we have the notebook for this application?
Can you share the code ?
yapcine
This is seriously the best co-hacking group in Ottawa. I always meet the best people there who are always so inspiring and helpful. 😄
One of the most underrated co-working/co-hacking space in all Ottawa. Thanks for featuring me 🤍
Spotted a lot of rockstars in this video! 🚀
You should really delve into this talk! Interesting perspective on critical thinking in LLMs.
Great talk! I especially liked all the quantization discussion. Right up my alley!
only a memer like him can make a long presentation exciting
I'm excited about the O-1 project and hearing about its growth.
How can I get this lambda shirt and GPU deal lol
DM kache haha
Nice, note it's drastically better story about webGPU compatibility these days :)
Dingverse
Im kinda getting ghost of Kiev vibes here ngl
fr
He does have a body and is not an anime character. Meatspace so weird.
real
Can't wait for the desktop app (on windows~)
Deeper voice than me lmao
Yo. I believe open interpreter is the absolute most underrated, under appreciated os ai model! Very impressed!
Thanks so much for recording this. I was not able to come as I anticipated
Amazing talk! To quote Willam Gibson - "The future has arrived - it’s just not evenly distributed yet."
This Open Interpreter thing sounds really nifty
its actually using juyipter to run the code ... this is a good method as it means mini kernals can be created for different dev kitss.... obviously using jupyter_Client without the note book .... but perhaps it should use notebooks for the sessions ... hence having the sessions stored in notebook form... as well as the environmenets can be created and reloaded for each project type, ie research toolts would be in a single notebook .... i think these guys have missed that the folder the interpreter uses to store code can be augmented by dropping modules inside the folder ....giving the model automatic skills by dropping them in the folder... there should also be a document cache for the model as it finds information it should convert them to text files to load as a rag when requred as the rag should be disposable ie session based but the text files static... such as txt,md,html,json etc... but its ok !! ipython/ikernal << even rund on android! <<< and some TV
Nice one guys : )
Brilliant idea! 🤯
Can’t wait!
Very insightful talk! I learned a lot!!
Awesome! The audio could be a bit louder, but otherwise a fantastic presentation. Thank you.
Yeah I messed up the camera's wireless mic this time so the audio quality wasn't top notch like the other vids.
Hey that's me! See you all in a month!
By the way, I love how you think. I'm so glad you're working on this. You are awesome!
When can I expect my 01 Lite? I ordered the device about 2 months ago with the understanding that had been released that the physical devices were available. I cannot find a way to contact the folks at Open Interpreter and I have not received my device. Really looking forward to working with the device. Any idea when I can expect my device?
I’m looking forward to using this 01 tool. I wish I had it now to help me install and use it now. lol
AttributeError: 'Killian' object has no attribute 'female' when starting interpreter from master branch.,, cant get past this bug!
You need to use attribute 'human'
@@theothergameygamercan confirm it works! Thanks ❤
How Killian hasn't been offered if not nearly unlimited funding, but plenty for every need to have a great staff moving the ball down the field on Open Interpreter is beyond me. Looking TREMENDOUSLY forward to their desktop app.
I agree I just hope the powers that be do not buy everyone out. Having an open source tool like this would probably be one of the biggest open source tools of our decade. I've learned so many command lines from just interpreter having something on a raspberry pi would be amazing. I do have the R1 and it is sad I cant even get inside an admin panel to tinker.