Skip to content
View Showmick119's full-sized avatar
9 followers · 3 following
  • Google
  • Atlanta, Georgia, United States
  • 06:15 (UTC -12:00)
  • LinkedIn in/showmick-das

Achievements

Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLO

Highlights

  • Pro

Block or report Showmick119

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
Showmick119/README.md

tl;dr

  • cs junior at georgia tech studying machine learning and systems architecture
  • currently working on search ai mode as a swe intern at google
  • prev contributed to openai's python sdk fixing critical memory leaks during high-volume batch uploads
  • prev built kv cache optimization frameworks and co-authored emnlp paper at gt's systems for ai lab
  • prev open-sourced neurips published research on foundational time-series modelling at gt's ai lab
  • enjoy lifting, running, sports (ufc, soccer, nba, f1, cricket), hip-hop, r&b, edm

Pinned Loading

  1. Code-Llama-7B-Training-Infrastructure Code-Llama-7B-Training-Infrastructure Public

    Infrastructure for fine-tuning the Code-Llama-7B model on code generation tasks, using 4-bit quantization, LoRA adapters and custom eval frameworks.

    Python

  2. Generative-Pretrained-Transformer Generative-Pretrained-Transformer Public

    Implementing the "Attention is All You Need" research paper from scratch, using only PyTorch and Mathematical Libraries.

    Jupyter Notebook

  3. Low-Latency-Market-Data-Parser Low-Latency-Market-Data-Parser Public

    A high-performance NASDAQ ITCH 5.0 protocol parser and order book engine written in C++20, designed for low-latency market data processing.

    C++ 1

  4. openai/openai-python openai/openai-python Public

    The official Python library for the OpenAI API

    Python 31.2k 5k