Skip to content
View Himanshu7921's full-sized avatar
16 followers · 6 following

Highlights

  • Pro

Block or report Himanshu7921

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.

Content in all repositories owned by your account will be closed.
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
Himanshu7921/README.md

Pinned Loading

  1. Optimization-Dynamics-Study Optimization-Dynamics-Study Public

    This repository studies how residual connections affect optimization stability in deep Transformers. Through controlled experiments and mathematical analysis, it examines gradient propagation, laye…

  2. BardGPT BardGPT Public

    BardGPT is a research-grade, decoder-only Transformer trained from scratch on the Tiny Shakespeare corpus, providing a clean, transparent, and extensible GPT-style architecture for experimentation …

    Python 7 2

  3. scratch-autoencoder scratch-autoencoder Public

    A fully-connected AutoEncoder for MNIST, implemented from scratch with custom layers, custom IDX dataloader, and research-grade training & visualization pipelines.

    Jupyter Notebook

  4. scratch-variational-autoencoder scratch-variational-autoencoder Public

    A fully-connected Variational AutoEncoder (VAE) for MNIST, implemented entirely from scratch with custom encoder–decoder architecture, reparameterization trick, handcrafted IDX dataloader, and rese…

    Jupyter Notebook

  5. DCGAN-PyTorch-Implementation-From-Scratch DCGAN-PyTorch-Implementation-From-Scratch Public

    PyTorch implementation of Deep Convolutional Generative Adversarial Networks (DCGAN) trained on the CelebA dataset

    Python