askai
nanoGPT
Our great sponsors
askai | nanoGPT | |
---|---|---|
1,746 | 69 | |
86 | 31,452 | |
- | - | |
10.0 | 5.4 | |
over 1 year ago | 25 days ago | |
TypeScript | Python | |
- | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
askai
-
How to build a custom GPT: Step-by-step tutorial
Go to chat.openai.com and log in
- Chat.openai.com no longer requires login
-
Integrating Strapi with ChatGPT and Next.js
In this tutorial, we will learn how to use Strapi, ChatGPT, and Next.js to build an app that displays recipes using AI.
-
GPT-4 Turbo with Vision is a step backwards for coding
Maybe I am bit dim, but how one can choose GPT-4 Turbo? Is this available from https://chat.openai.com/ ?
-
AI Developer Tool Limitations In 2024
With the rise of ChatGPT, Bard Gemini, GitHub Copilot, Devin, and other AI tools1, developers started to fear that AI tooling would replace them. Even though their capabilities are indeed impressive, I don't fear our jobs will go away in 2024.
-
Data-driven customer acquisition: Machine Learning applied to Customer Lifetime Value
To illustrate the core concepts of ML and regression analysis, we’ll start with a simple model. ChatGPT (the free version) creates something that works with this prompt:
-
From 12th Final Project to an ATM Management System: Leveraging ChatGPT 4 for PDF Analysis
Fast forward to my college years. I found myself at IIIT Delhi, a prestigious tier 1 computer science engineering college. Around the same time, ChatGPT emerged, shaking the world more vigorously than COVID-19. As fate would have it, I gained temporary access to ChatGPT 4 which runs on GPT 4, and curiosity piqued my interest.
-
📊 Obsidian: Nutrition
It is worth mentioning that for my use case, I do not require a high level of precision, so I obtain the values with an AI. I describe the recipe and portions to ChatGPT, and it provides me with a very good estimate of the nutritional information of the meal.
- Exploring the Frontiers of AI: An In-Depth Look at ChatGPT-4
-
How to connect ChatGPT to a SQL database for data retrieval and analysis
To be able to work with chatGPT, head over to ChatGPT and sign up if you haven't already. If you have signed up, all you need to do is log in
nanoGPT
-
Show HN: Predictive Text Using Only 13KB of JavaScript. No LLM
Nice work! I built something similar years ago and I did compile the probabilities based on a corpus of text (public domain books) in an attempt to produce writing in the style of various authors. The results were actually quite similar to the output of nanoGPT[0]. It was very unoptimized and everything was kept in memory. I also knew nothing about embeddings at the time and only a little about NLP techniques that would certainly have helped. Using a graph database would have probably been better than the datastructure I came up with at the time. You should look into stuff like Datalog, Tries[1], and N-Triples[2] for more inspiration.
You're idea of splitting the probabilities based on whether you're starting the sentence or finishing it is interesting but you might be able to benefit from an approach that creates a "window" of text you can use for lookup, using an LCS[3] algorithm could do that. There's probably a lot of optimization you could do based on the probabilities of different sequences, I think this was the fundamental thing I was exploring in my project.
Seeing this has inspired me further to consider working on that project again at some point.
[0] https://github.com/karpathy/nanoGPT
[1] https://en.wikipedia.org/wiki/Trie
[2] https://en.wikipedia.org/wiki/N-Triples
[3] https://en.wikipedia.org/wiki/Longest_common_subsequence
-
LLMs Learn to Be "Generative"
where x1 denotes the 1st token, x2 denotes the 2nd token and so on, respectively.
I understand the conditional terms p(x_n|...) where we use cross-entropy to calculate their losses. However, I'm unsure about the probability of the very first token p(x1). How is it calculated? Is it in some configurations of the training process, or in the model architecture, or in the loss function?
IMHO, if the model doesn't learn p(x1) properly, the entire formula for Bayes' rule cannot be completed, and we can't refer to LLMs as "truly generative". Am I missing something here?
I asked the same question on nanoGPT repo: https://github.com/karpathy/nanoGPT/issues/432, but I haven't found the answer I'm looking for yet. Could someone please enlighten me.
-
A simulation of me: fine-tuning an LLM on 240k text messages
This repo, albeit "old" in regards to how much progress there's been in LLMs, has great simple tutorials right there eg. fine-tuning GPT2 with Shakespeare: https://github.com/karpathy/nanoGPT
-
Ask HN: Is it feasible to train my own LLM?
For training from scratch, maybe a small model like https://github.com/karpathy/nanoGPT or tinyllama. Perhaps with quantization.
-
Writing a C compiler in 500 lines of Python
It does remind me of a project [1] Andrej Karpathy did, writing a neural network and training code in ~600 lines (although networks have easier logic to code than a compiler).
-
[D] Can GPT "understand"?
But I'm still not convinced that it can't in theory. Maybe the training set or transformer size I'm using is too small. I'm using nanoGPT implementation (https://github.com/karpathy/nanoGPT) with layers 24, heads 12, and embeddings per head 32. I'm using character-based vocab: every digit is a separate token, +, = and EOL.
-
Transformer Attention is off by one
https://github.com/karpathy/nanoGPT/blob/f08abb45bd2285627d1...
At training time, probabilities for the next token are computed for each position, so if we feed in a sequence of n tokens, we basically get n training examples, one for each position, but at inference time, we only compute the next token since we’ve already output the preceding ones.
-
Sarah Silverman Sues ChatGPT Creator for Copyright Infringement
And there are a bunch of other efforts at making training more efficient. Here's a cool model by Karpathy (OpenAI/used to head up Tesla's efforts): https://github.com/karpathy/nanoGPT
-
Douglas Hofstadter changes his mind on Deep Learning and AI risk
Just being a part of any auto-regressive system does not contradict his statement.
Go look at the GPT training code, here is the exact line: https://github.com/karpathy/nanoGPT/blob/master/train.py#L12...
The model is only trained to predict the next token. The training regime is purely next-token prediction. There is no loopiness whatsoever here, strange or ordinary.
Just because you take that feedforward neural network and wrap it in a loop to feed it its own output does not change the architecture of the neural net itself. The neural network was trained in one direction and runs in one direction. Hofstadter is surprised that such an architecture yields something that looks like intelligence.
He specifically used the correct term "feedforward" to constrast with recurrent neural networks, which GPT is not: https://en.wikipedia.org/wiki/Feedforward_neural_network
-
NTK-Aware Scaled RoPE allows LLaMA models to have extended (8k+) context size without any fine-tuning and minimal perplexity degradation.
Does anyone have or know of an example implementation in plain pytorch, not huggingface transformers. Like something you could plug into https://github.com/karpathy/nanoGPT ?
What are some alternatives?
ChatGPT - 🔮 ChatGPT Desktop Application (Mac, Windows and Linux)
minGPT - A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
gpt-4chan-model
RWKV-LM - RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
openai-cookbook - Examples and guides for using the OpenAI API
PaLM-rlhf-pytorch - Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
ai-cli - Get answers for CLI commands from ChatGPT right from your terminal
KoboldAI-Client
nn-zero-to-hero - Neural Networks: Zero to Hero
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
gpt_index - LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data. [Moved to: https://github.com/jerryjliu/llama_index]