minGPT
mwparserfromhell
minGPT | mwparserfromhell | |
---|---|---|
35 | 5 | |
19,037 | 708 | |
- | - | |
0.0 | 6.6 | |
23 days ago | 16 days ago | |
Python | Python | |
MIT License | 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.
minGPT
- FLaNK AI Weekly for 29 April 2024
-
Ask HN: Daily practices for building AI/ML skills?
minGPT (Karpathy): https://github.com/karpathy/minGPT
Next, some foundational textbooks for general ML and deep learning:
-
[D] What are some examples of being clever with batching for training efficiency?
Language Model novice here. I was going through the README section of minGPT and read this line.
-
LLM Visualization: 3D interactive model of a GPT-style LLM network running inference.
The first network displayed with working weights is a tiny such network, which sorts a small list of the letters A, B, and C. This is the demo example model from Andrej Karpathy's minGPT implementation.
- LLM Visualization
- Learn Machine Learning
-
Facebook Prophet: library for generating forecasts from any time series data
Tried it once. Its promise is to take the dataset's seasonal trend into account, which makes sense for Facebook's original use case.
We ran it on such a dataset and found out that directly using https://github.com/karpathy/minGPT consistently gives a better result. So we ended up using the output of Prophet as an input feature to a neural network, but the result was not improved in any significant way.
-
Tokenization of numerical series
Sure, im trying to regenerate a bunch of complex numbers based on their absolute value. So im trying to embed these absolute values and then using gpt model(probably mini gpt) try to recover the original comples numbers. There is a certain connection between these complex numbers and their order which im not capable of explaining yet. Im hoping the model would be capable of recognizing certain sequences of these absolute values and match them with the desired complex counterparts (by training the model).
-
Anyone know of any articles on training a LLM from scratch on a single GPU?
minGPT (https://github.com/karpathy/minGPT)
-
Understanding LLMs(to the best of our knowledge)
Check out minGPT and nanoGPT from Karpathy, he puts out some of the best machine learning tutorials and teaching content.
mwparserfromhell
- FLaNK AI Weekly for 29 April 2024
-
Processing Wikipedia Dumps With Python
There's also https://github.com/earwig/mwparserfromhell, if you don't want to roll your own.
-
[Python] How can I clean up Wikipedia's XML backup dump to create dictionaries of commonly used words for multiple languages?
In particular what you're looking at is not XML but wikitext. I found a discussion on stackoverflow about solving the same problem of getting text from wikitext. Seems like the most promising solution in Python since you already have the dump is to run each page through mwparserfromhell. According to the top stackoverflow answer you could use something like
-
How can I clean up Wikipedia's XML backup dump to create dictionaries of commonly used words for multiple languages?
Thank you so much! I was actually talking about the markup language within the text. Turns out it's proprietary to WikiMedia and user lowerthansound kindly suggested I use this: https://github.com/earwig/mwparserfromhell
What are some alternatives?
nanoGPT - The simplest, fastest repository for training/finetuning medium-sized GPTs.
wikitextparser - A Python library to parse MediaWiki WikiText
gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners"
archwiki - MediaWiki used on Arch Linux websites (read-only mirror)
simpletransformers - Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
WiktionaryParser - A Python Wiktionary Parser
Pytorch-Simple-Transformer - A simple transformer implementation without difficult syntax and extra bells and whistles.
wikiteam - Tools for downloading and preserving wikis. We archive wikis, from Wikipedia to tiniest wikis. As of 2023, WikiTeam has preserved more than 350,000 wikis.
nn-zero-to-hero - Neural Networks: Zero to Hero
pywikibot - A Python library that interfaces with the MediaWiki API. This is a mirror from gerrit.wikimedia.org. Do not submit any patches here. See https://www.mediawiki.org/wiki/Developer_account for contributing.
huggingface_hub - The official Python client for the Huggingface Hub.
isbntools - python app/framework for 'all things ISBN' including metadata, descriptions, covers...