Skip to content
View sanyalsunny111's full-sized avatar

Block or report sanyalsunny111

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 supported. This note will be visible to only you.
Report abuse

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

Report abuse
sanyalsunny111/README.md

Hi, I'm Sunny πŸ‘‹

  • πŸŽ“ I'm a final year PhD student at UT Austin, advised by Prof. Sujay Sanghavi.
  • πŸ€– My research focuses on efficient training recipes for Large Models (pre-training, fine-tuning, and continual learning).
  • πŸ“« Reach me at: Homepage Β· Twitter/X

πŸ“Š GitHub Stats

Sunny's GitHub stats


πŸš€ Selected Open-Source Contributions


Pinned Loading

  1. LLM-Inheritune LLM-Inheritune Public

    [TMLR 2025] When Attention Collapses: How Degenerate Layers in LLMs Enable Smaller, Stronger Models

    Jupyter Notebook 122 10

  2. Early_Weight_Avg Early_Weight_Avg Public

    [COLM 2024] Early Weight Averaging meets High Learning Rates for LLM Pre-training

    Python 19 1

  3. FLOW_finetuning FLOW_finetuning Public

    Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting

    Python 5 4

  4. Looped-GPT Looped-GPT Public

    Minimal and highly hackable implementation of Looped Transformers with GPT

    Python 20 1