Jeremy Howard provides a practical guide to language models, covering GPT-4 capabilities, API usage, fine-tuning, and local deployment.
In this deeply informative video, Jeremy Howard, co-founder of fast.ai and creator of the ULMFiT approach on which all modern language models (LMs) are based, takes you on a comprehensive journey through the fascinating landscape of LMs. Starting with the foundational concepts, Jeremy introduces the architecture and mechanics that make these AI systems tick. He then delves into critical evaluations of GPT-4, illuminates practical uses of language models in code writing and data analysis, and offers hands-on tips for working with the OpenAI API. The video also provides expert guidance on technical topics such as fine-tuning, decoding tokens, and running private instances of GPT models.
As we move further into the intricacies, Jeremy unpacks advanced strategies for model testing and optimization, utilizing tools like GPTQ and Hugging Face Transformers. He also explores the potential of specialized datasets like Orca and Platypus for fine-tuning and discusses cutting-edge trends in Retrieval Augmented Generation and information retrieval. Whether you're new to the field or an established professional, this presentation offers a wealth of insights to help you navigate the ever-evolving world of language models.
(The above summary was, of course, created by an LLM!)
For the notebook used in this talk, see github.com/fastai/lm-hackers.
Introduction & Basic Ideas of Language Models
Limitations & Capabilities of GPT-4
AI Applications in Code Writing, Data Analysis & OCR
Practical Tips on Using OpenAI API
Creating a Code Interpreter with Function Calling
Using Local Language Models & GPU Options
Fine-Tuning Models & Decoding Tokens
Testing & Optimizing Models
Retrieval Augmented Generation
Fine-Tuning Models
Running Models on Macs
Llama.cpp & Its Cross-Platform Abilities
This is an extended version of the keynote given at posit::conf(2023). Thanks to @wolpumba4099 for chapter titles.
Why it's here
8 people recommend this
What people say. Highly recommended as the best practical tutorial on understanding, using, and fine-tuning large language models.
t
tarrudaon Hacker News • Recommends
On “A Hackers' Guide to Language Models [video]”
Thanks a lot for this video, best LLM usage tutorial I've seen so far. At link to this video 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 s…
An interesting solution to the blind spot error (taken directly from Jeremy Howard's amazing guide to language models - link to this video ) is to erase the chat history and try again. Once GPT has made an error (or as the author of this article says, the early layers have irreversibly pruned some important data), it will very often start to be even more wrong.
If you're looking for a practical guide on how to use LLMs, highly recommend "Hackers Guide to language models" by Jeremy Howard. 1.5h video packed with practical information: link to this video
…ongly strongly recommend starting with karpathy's from 0 to hero neural networks youtube course - it starts with building a tensor library and back propagation, explaining it in a way that finally clicked for me link jeremy howard also has a fantastic video that is more around how to use LLMs and such called a hacker's guide to language models - link to this video as i've dove more and more into it, i would strongly recommend trying to run things on your local machine too (llama.cpp, ollama, LM studio). that has helped me fight that feeling of like "are we all just going to be open AI developers in the end" and made me feel like you _can_ integrate these things into stuff you build by your self. I ca…
Jeremy Howard talks about it in his recent video "A Hackers' Guide to Language Models": link to this video That link goes directly to the timestamp where he discusses fine tuning, but the whole talk is great. Punchline, check out Axolotl: link
…he benchmarks against which GPT3, InstructGPT, and GPT4 were tested are illuminating about its problem solving ability on novel problems, these are described in the three respective papers. Secondly, quality is highly variant and there are traps the context window can fall into which causes especially bad results. Jeremy Howard has a great video ( link to this video , starting at 18:05 the 'limitations and capabilities' section is only 13 minutes long) talking about how quality depends on: how you frame your prompts, model power (4 does a lot of stuff that 3.5 can't), and whether you're in a kind of "context trap" of repeated mistakes. Of course, some people like to point out that if it's so "finicky"…
Will you still be working on educational content on the side? (e.g. updating fast.ai and/or making one off lectures like link to this video ) Either way thank you for all the amazing free content you've already put out and good luck on the new endeavor!
On “GPT-4, without specialized training, beat a GPT-3.5 class model that cost $10M”
For "citation needed", read "please link me to a blog post showing how, don't just tell me to Google for one". The internet is full of blog posts about this. That doesn't mean they're actually good - I'd love to be pointed at one that has proven itself useful for someone (and definitely isn't just LLM blog-spam). I don't care if it's trivial to fine-tune and get crap results - I care about fine-tuning where the result was worth the effort. For the record, my favourite guide to fine-tuning is the section of this Jeremy Howard video that shows how to train a text-to-SQL model: link to this video
I suspect these videos would be higher quality than most offerings from universities or business schools (given that it's a fast moving field, and most of the true experts are practitioners, and so if they're teaching, they're not teaching actual classes, at most they're doing youtube videos or interviews): - link to this video (Jeremy Howard Hacker's Guide to LLMs) - link (Karpathy Intro to LLMs)
On “Ask HN: Recommendation for a SWE looking to get up to speed with latest on AI”
It sounds like you want more broad stuff, not necessarily learning how to train models. More like learning to use them and how they work. link and Hacker's Guide to LLMs by Jeremy from Fast.ai - link to this video State of GPT by Karpathy - link LLMs by 3b1b - link Visualizing transformers by 3b1b - link How ChatGPT trained - link AI in a nutshell - link How Carlini uses LLMs - link For staying updated: X/Twitter & Bluesky. Go and follow people that work at OpenAI, Anthropic, Google DeepMind, and xAI. Podcasts: No Priors, Generally Intelligent, Dwarkesh Patel, Sequoia's "Training Data"
On “LLMs and the End of Programming – CS50 Tech Talk with Dr. Matt Welsh [video]”
Jeremy Howard put a nice example in his Video 'A Hackers' Guide to Language Models' 0. He asked a LLM to solve the 'Wolf, goat and cabbage problem' 1, which it could do without a problem. When he modified the problem in a way, that made it trivially solvable by a reasoning human, the LLM failed miserably. It kept parroting the solution to the original problem. 0link to this video1link
On “Ask HN: What ChatGPT prompt do you use to avoid code-writing hallucinations?”
…general so you don't need to remind them about those either. > > Don't be verbose in your answers, but do provide details and examples where it might help the explanation. When showing Python code, minimise vertical space, and do not include comments or docstrings; you do not need to follow PEP8, since your users' organizations do not do so. 0 - link to this video…
