วีดีโอ

Nicely Explained!

SingleStore DB has hybrid search capabilities.

I'm also nice to my chat gpt sessions, but equally abusive when I fail to prompt it well

no questions usually mean - you know what.. examples of the slides are terribly biased, not sure how that can be effective campaign or product

what exactly is a parameter in llm? what do you mean when you say this model has 1 billion parameters?

Nice

nothing new, just recycled existing information on this topic, very disappointing ...

Absolutely amazing! Thank you so much for this.

🎯 Key Takeaways for quick navigation: 00:29 🤖 Sebastian Raschka is the lead AI educator for Lightning AI and a former professor of Statistics. 00:43 🤔 LLMs (Large Language Models) promise to make us more productive by speeding up tasks like writing emails and coding. 01:52 🦾 Sebastian discusses the motivation behind caring about LLMs, including staying updated with news and the potential for increased productivity. 04:09 🎛️ LLMs like ChatGPT go through three main stages: pre-training, supervised fine-tuning, and alignment. 07:37 💡 The pre-training and fine-tuning stages involve next word prediction tasks, but the format of the data sets and instructions differ. 10:09 🤖 LLMs (Large Language Models) go through a three-stage process: pre-training, fine-tuning, and alignment. 11:31 🦾 Reinforcement Learning from Human Feedback (RLHF) involves sampling prompts, having humans rank the responses, training a reward model, and refining the model using proximal policy optimization. 13:21 💡 When it comes to using LLMs, there are five main ways: everyday tasks, pre-training and prompting for specific domains, fine-tuning on specific data, fine-tuning and prompting for code-related tasks, and training custom models. 16:36 👥 Bloomberg pre-trained their own LLM on general data and finance-specific data to generate a proprietary database format and finance news headlines. 18:13 🐍 Meta AI (formerly Facebook) trained the Code LLM by pre-training a model, further training it on general code data, fine-tuning it on python code, and iterating through various fine-tuning stages to create models like Code Llama. 19:07 👥 Open source LLMs provide access to log probabilities, allowing for analyzing the confidence of the model and ranking responses. 21:24 🤖 Open source LLMs provide privacy and control as the data never has to leave the computer and can be modified as desired. 23:19 👍 Open source LLMs offer full customizability and allow for experimentation and modifications to the model. 24:30 💡 Open source LLMs do not change unless desired, which can be an advantage or disadvantage depending on the need for updates. 25:40 🔌 Running open source LLMs requires access to hardware and some additional work in terms of cloning repositories and downloading weights. 30:02 👥 Open source models like Free Willy Falcon, Bikuna, PhysioStable, Code Llama, and Lit GPT offer freely available weights and a hackable, customizable codebase. 31:27 🏢 Fine-tuning smaller models can achieve better performance on specific tasks than using larger general models like GPT-3 or GPT-4. 32:49 💡 Fine-tuning models are task-specific and useful for solving specific business problems, while prompting models are more general-purpose. 34:40 ⏱️ Parameter-efficient fine-tuning techniques like adapters and low-rank adaptation (Laura) can save a significant amount of time compared to full fine-tuning. 37:12 🌟 Future trends for LLMs include the mixture of experts approach, multi-modal models, and LLMs for specific domains like protein-related tasks. 39:33 🎯 Non-transformer large language models like RWKV, hyena hierarchy, and retentive Network offer alternative approaches to language modeling that are worth keeping an eye on. 39:49 🔄 There are alternatives to reinforcement learning-based fine-tuning, such as relabeling data in hindsight and direct policy optimization, which show promising results and may simplify the process. 41:22 🌐 The performance of fine-tuned models can vary based on the specificity of the domain, with the potential to outperform larger pre-trained models in smaller, more specific domains. 41:09 📚 Sebastian Raschka stays updated on new research papers and frequently discusses them on his blog. He is also involved in developing the open-source repository Electricity for loading and customizing LLMs. 41:40 🎙️ There is no size limit for the domain when it comes to outperforming pre-trained models with fine-tuned models. The performance can vary based on the specific task and the domain covered. Made with HARPA AI

1 minus cosine similarity? Why?

Good but, how does it compare against the other vector DBs?

Can we search through the documents "which targets specific information"? Suppose, I want to search for the articles which talk about "young males in their 20s". Now, that doesn't necessarily look for that phrase because it is unlikely that it will be the case. Then how would I search like that? Should I pass metadata? How to pass additional information that can be used to filter the documents for the retrival?

Vector addition is high level term?

Thanks for a presentation

Come on people, his jokes weren't that bad.

Great speaking skills by Sam. Vector databases are going to partner with LLMs beautifully.

Great explanation

ai datab bases

I can't find the blog

Is there a possibility if we can get the presentation deck?

Ol

Thanks for sharing this ! This presentation was very valuable. This 3rd generation view(past, present, future) raises a lot of questions in my mind. • What business areas(industry, agriculture, constructions, small business) we could apply the machine learning techniques to improve productivity ? • How to turn a vast amount of tabular data available into good resources(good raw material) for theses models? • How to acquire better quality, standardized and comparable data (e.g. sensors, transfer learning from dl models etc) ? Thank you all for sharing with us and congratulations Mr. Tunguz for this presentation.

Good Talk

One of the most undervalued projects! Happy to had/have the chance to know about it before it skyrockets!

Like bro!)

I loved this technical presentation! I've been using Presearch for a long time and have two nodes. The engine is already running very well! I invite everyone to try it.

Outstanding yes, thanks for your talk

Nice job Trey! Looking forward to seeing the rollout of additional node roles in the near future!

Outstanding presentation... Thanks Trey for an explanation that even a novice such as me can understand! : ) 💪💪💪

Amazing work Trey you are the best for Presearch, here I am migrating a node from RN jaja. Keep rocking