InkChatGPT
stat_rethinking_2024
InkChatGPT | stat_rethinking_2024 | |
---|---|---|
1 | 3 | |
6 | 752 | |
- | - | |
9.1 | 6.9 | |
7 days ago | 3 months ago | |
Python | R | |
MIT License | Creative Commons Zero v1.0 Universal |
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.
InkChatGPT
-
Ask HN: What Are You Learning?
I'm learning LLM at the moment, RAG particularly. [1]
I ended up built InkChatGPT as my learning project and it was huge fun. It is an AI Agent that could help learning from multiple documents and you can chat with it, thank Chat PDF GPT.
I use LangChain as LLM framework to simplify the backend, and using Streamlit as front end UI and deployment. Using OpenAI `gpt-3.5-turbo` model, Use HuggingFace embeddings to generate embeddings for the document chunks with `all-MiniLM-L6-v2` model.
To be honest, coming from Mobile development background, learning about ML and reading about LLM models, prompt tuning and various techniques really opens my mind, but the vast information and knowing how to start is difficult.
[1] InkChatGPT: https://github.com/vinhnx/InkChatGPT
stat_rethinking_2024
-
Ask HN: What Are You Learning?
+1 for the Rethinking Statistics book by McElreath. I recently took the 2024 edition of the self-paced course https://github.com/rmcelreath/stat_rethinking_2024 and the lectures on youtube are amazing. He's not just teaching stats, but how to do science!
Another, more basic, book on Bayesian stats is: https://allendowney.github.io/ThinkBayes2/ The author uses the grid approximation for everything, so there is no need to get into Stan or other framework.
Myself, I'm still trying to (re)learn frequentist stuff properly (will post a separate comment about that), but the deeper I go the more convinced I am that it is total crap, and my desire to convert to the church of Bayes increases...
-
Bayesians Moving from Defense to Offense
Thanks for the "Statistical Rethinking" recommendation. I had watched some of McElreath's lectures so I knew of the book, but next year I think I'm finally going to read it from end to end and follow along the 2024 course schedule: https://github.com/rmcelreath/stat_rethinking_2024#calendar-...
I had previously started the BDA course, which is another famous Bayesian course, see https://avehtari.github.io/BDA_course_Aalto/ but I didn't finish it due to travel.
No more excuses in 2024... time to level-up the Bayesian modelling skill ;)
- Statistical Rethinking (2024 Edition)
What are some alternatives?
selkokortti - Generate Anki flashcards from Andrew's Selkouutiset Archive. Contributions welcome!
gol - Haskell implementation of Conways' Game of Life.