LLMs-from-scratch
heynote
LLMs-from-scratch | heynote | |
---|---|---|
9 | 7 | |
16,129 | 3,524 | |
- | - | |
9.6 | 9.2 | |
1 day ago | about 2 months ago | |
Jupyter Notebook | JavaScript | |
GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
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...)
heynote
-
LaTeX and Neovim for technical note-taking
Most of my technical note-taking these days happens inside VS Code. I already have it running, so opening a new window and stripping out the chrome (closing other stuff, hiding sidebars, etc. gives me all I need, _plus_ optional preview depending on on what I'm writing (mostly Markdown these days).
Another option some of my friends like is Heynote (https://heynote.com), but, again, I can do the same with VS Code...
- FLaNK Stack 29 Jan 2024
-
Why I Like Obsidian
obsidian is good for what it does, but in the last month I saw someone share heynote[1] with me that I have grown fond of as a support to my obsidian note taking
[1] https://heynote.com
- FLaNK Weekly 08 Jan 2024
-
Show HN: Heynote – A Dedicated Scratchpad for Developers
I’m eagerly waiting for the vi bindings as well!
P.S.: had a quick glance through the PRs after using it for sometime and saw a draft PR for vi bindings already! - https://github.com/heyman/heynote/pull/51
What are some alternatives?
s4 - Structured state space sequence models
codi.vim - :notebook_with_decorative_cover: The interactive scratchpad for hackers.
logseq - A local-first, non-linear, outliner notebook for organizing and sharing your personal knowledge base. Use it to organize your todo list, to write your journals, or to record your unique life.
mathjs - An extensive math library for JavaScript and Node.js
pong-wars
fend - Arbitrary-precision unit-aware calculator
todo.txt-cli - ☑️ A simple and extensible shell script for managing your todo.txt file.
Trilium Notes - Build your personal knowledge base with Trilium Notes
notecalc3 - NoteCalc is a handy calculator trying to bring the advantages of Soulver to the web.
dev - Development repository for the CodeMirror editor project
llm-classifier - Classify data instantly using an LLM
NotePlan_Themes - Official collection of custom themes for NotePlan 3