-
Contextual Robotics Institute
- San Diego, California, United States
- https://saqib1707.github.io
- @_saqib1707
Lists (1)
Sort Name ascending (A-Z)
Stars
Code Implementation for Object 6D Pose Estimation
Efficient Triton Kernels for LLM Training
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Code for the paper "Language Models are Unsupervised Multitask Learners"
A collection of full time roles in SWE, Quant, and PM for new grads.
Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models)
Collection of Summer 2025 tech internships!
llama3 implementation one matrix multiplication at a time
A Simplified PyTorch Implementation of Vision Transformer (ViT)
Video+code lecture on building nanoGPT from scratch
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Scenic: A Jax Library for Computer Vision Research and Beyond
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
A Spatio-temporal Transformer for 3D Human Motion Prediction
An autoregressive character-level language model for making more things
Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/
Implementation of basic ML algorithms from scratch in python...
Implementation of the paper "Language-agnostic representation learning of source code from structure and context".
A concise but complete full-attention transformer with a set of promising experimental features from various papers
Implementation of Convolutional LSTM in PyTorch.
How to build RNNs and LSTMs from scratch with NumPy.
Adaptive FNO transformer - official Pytorch implementation
Faster way to switch between clusters and namespaces in kubectl
A minimalist, open source online pastebin where the server has zero knowledge of pasted data. Data is encrypted/decrypted in the browser using 256 bits AES.
Worldwide building footprints derived from satellite imagery
Computer generated building footprints for the United States
A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.