LLMs-from-scratch
finagg
LLMs-from-scratch | finagg | |
---|---|---|
9 | 17 | |
16,129 | 385 | |
- | - | |
9.6 | 8.1 | |
about 22 hours ago | about 18 hours ago | |
Jupyter Notebook | Python | |
GNU General Public License v3.0 or later | Apache License 2.0 |
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.
LLMs-from-scratch
- Finetune a GPT Model for Spam Detection on Your Laptop in Just 5 Minutes
- Insights from Finetuning LLMs for Classification Tasks
-
Ask HN: Textbook Regarding LLMs
https://www.manning.com/books/build-a-large-language-model-f...
- Comparing 5 ways to implement Multihead Attention in PyTorch
- FLaNK Stack 29 Jan 2024
-
Implementing a ChatGPT-like LLM from scratch, step by step
The attention mechanism we implement in this book* is specific to LLMs in terms of the text inputs, but it's fundamentally the same attention mechanism that is used in vision transformers. The only difference is that in LLMs, you turn text into tokens, and convert these tokens into vector embeddings that go into an LLM. In vision transformers, instead of regarding images as tokens, you use an image patch as a token and turn those into vector embeddings (a bit hard to explain without visuals here). In both text or vision context, it's the same attention mechanism, and it both cases it receives vector embeddings.
(*Chapter 3, already submitted last week and should be online in the MEAP soon, in the meantime the code along with the notes is also available here: https://github.com/rasbt/LLMs-from-scratch/blob/main/ch03/01...)
finagg
-
This Week In Python
finagg – A Python package for aggregating and normalizing historical data from popular and free financial APIs
- FLaNK Stack 29 Jan 2024
- Show HN: Finagg – free and nearly unlimited financial data
-
[D] Website to get historical price for agriculture commodities?
This is certainly a weird place to ask this question. That being said, you should explore the FRED API. Here's my project that implements most of it in Python: https://github.com/theOGognf/finagg The walkthrough shows you how to find what you're looking for
-
Fundamental Data Sources
I created a Python package exactly for this. https://github.com/theOGognf/finagg. It aggregates historical fundamental data for whatever tickers you specify or from a subset of tickers. Let me know what you think
-
Is accurate quarterly earnings data availible?
This package https://github.com/theOGognf/finagg already implements the complete SEC EDGAR REST API (disclaimer: I'm the author), and the archive-based API is in the works. I suggest you give it a go using the latest version off GitHub
-
Sunday Daily Thread: What's everyone working on this week?
I've got some time set aside to implement a (file based) SEC EDGAR API described in this issue https://github.com/theOGognf/finagg/issues/43
- finagg: NEW Data - star count:107.0
What are some alternatives?
s4 - Structured state space sequence models
pyautoenv - Automatically activate and deactivate Python environments as you move around the file system.
sql-to-kml - Format SQL query results into a KML file.
plombery - Python task scheduler with a user-friendly web UI
usepython - Run Python scripts in a Pyodide service worker
bytewax - Python Stream Processing
java-snapshot-testing - Facebook style snapshot testing for JAVA Tests
internet-speed-test - An Internet Speed Test built on Python's Turtle module
uuid-utils - Python bindings to Rust UUID
pong-wars
pyodide - Pyodide is a Python distribution for the browser and Node.js based on WebAssembly
pyxfl - a work in progress python library to query xfl statistics