Skip to content
View raghulchandramouli's full-sized avatar
🎯
Focusing
🎯
Focusing
27 followers · 24 following

Achievements

Achievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: YOLOAchievement: Pull Shark

Achievements

Achievement: Pair ExtraordinaireAchievement: QuickdrawAchievement: YOLOAchievement: Pull Shark

Highlights

Block or report raghulchandramouli

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
raghulchandramouli/README.md

What I'm Up To

I read research papers for "fun," try to reimplement them and usually end up debugging my life choices more than my code

  • Currently Learning/doing:
    • Pre-training — extracting patterns from raw tokens faster than I extract them from experience
    • Mech Interp - aka Mission Impossible: decoding neural nets before they decode me

Quote I live by: If you don't succeed, blame the author of the paper or its just following the laws of modern ML...

Pinned Loading

  1. Remaskable Remaskable Public

    A No-Code Annotation platform for Image-Synthetic Generation Tasks

    Python 1

  2. Manifold-representations Manifold-representations Public

    Jupyter Notebook

  3. Mechanistic-Qwen Mechanistic-Qwen Public

    A KL-div + Token-level Analysis of Qwen and DeepSeek model for Reasoning

    Jupyter Notebook

  4. optax optax Public

    Forked from google-deepmind/optax

    Optax is a gradient processing and optimization library for JAX.

    Python