As the original author, can you rate this ai generated summary of your video:

Video tutorial on language models by Jeremy Howard from fast.ai. In the tutorial, Howard explains the basics of language models and how to use them in practice. He starts by defining a language model as something that can predict the next word of a sentence or fill in missing words. He demonstrates this using an open AI language model called text DaVinci 003.

Howard explains that language models work by predicting the probability of various possible next words based on the given context. He shows how to use language models for creative brainstorming and playing with different word predictions.

He then discusses language model training and fine-tuning processes, using the ULMfit approach as an example. He explains the three steps of language model training: pre-training, language model fine-tuning, and classifier fine-tuning. He mentions the importance of fine-tuning language models for specific tasks to make them more useful.

Howard also demonstrates how to use the open AI API to access language models programmatically. He shows examples of using the API to generate text, ask questions, perform code interpretation, and even extract text from images using OCR.

Additionally, he discusses the options for running language models on your own computer, such as using GPUs, renting GPU servers, or utilizing cloud platforms like Kaggle and Colab.

He mentions the Transformers library from Hugging Face, which provides pre-trained models and data sets for language processing tasks. He highlights the benefits of fine-tuning models and using retrieval augmented generation to combine document retrieval with language generation.

The tutorial concludes with a discussion on other options for running language models, including using private GPT models, Mac-based solutions like H2O GPT and lima.cpp, and the possibility of fine-tuning models with custom data sets.

Overall, the tutorial provides a comprehensive overview of language models, their applications, and different ways to use them, both with open AI models and on your own computer.

I think that summary is pretty good, although it doesn't really highlight the most interesting bits, such as the fact that we implement a code interpreter from scratch, and that we cover fine-tuning to create a model that successfully converts prose questions into SQL queries.

I actually just created my own summary of the bits I'm most excited about, in case it's helpful to folks: https://twitter.com/jeremyphoward/status/1705883362991472984

Thanks a lot for this video, best LLM usage tutorial I've seen so far.

At https://youtu.be/jkrNMKz9pWU?si=Dvz-Hs4InJXNozhi&t=3278 when talking about valid use cases for a local model vs GPT4 is: "You might want to create your own model that's particularly good at solving the kinds of problems that you need to solve using fine tuning, and these are all things that you absolutely can get better than GPT4 performance".

In regards to this, there's an idea I've been thinking about for some time: Imagine a chatbot that is backed by multiple "small" models (such as 7B parameters), where each model is fine tuned for a specific task. Could such a system outperform GPT4?

Here's a high level overview how I imagine this to work:

- Context/prompt is sent to a "router model", which is trained to determine what kind of expert model can best answer/complete the prompt. - The system then passes the context/prompt to the expert model and returns that answer. - If no expert model is found, just use a generic instruct tuned general purpose LLM to answer

If you can theoretically get better than GPT4 performance on a small models fine tuned for that task, maybe a cluster of such small models could collectively outperform GPT4.

Does that make sense?

Search "mixture of experts" on Google, some unverified leaks say GPT4 is using it already.

Can you share where you read about these leaks?

It was all over hackernews. Just google "hacker news gpt4 mixture of experts".

George Hotz was the first to mention on Lex Fridman’s podcast, and there have been several others close to OpenAI who confirmed.

It makes a lot of sense! In fact there's a number of open source projects working on just such a model right now. Here's a great example: https://github.com/XueFuzhao/OpenMoE/

Awesome, thanks for sharing.

Sambanova just launched something similar to what you're describing. It's a demo of their new chip running a 1T param MoE model 150 7B llama2s, each retrained to be an expert in a different topic. So one of them is a "law" expert, another on "physics", etc.

They've got a video here [1] (scroll down slightly) that compares it against a 180B Falcon model that's running on GPUs on HuggingFace. The MoE results are not only just as good quality-wise, but also ridiculously fast. Like, nearly instant. A big benefit is that the experts can be swapped-out and retrained with new data, which is obviously not as easy with the more monolithic 180B model.

[1] https://sambanova.ai/launch2023

Really impressive, thanks for sharing

You're a legend, thank you. You're admired all around the world.