Sankeerth Rao Karingula's Projects
Testing out the OpenAI features launched on Dev Day
Resources of deep learning for mathematical reasoning (DL4MATH).
JAX-based neural network library
Data processing system for polyglot
Draco is a library for compressing and decompressing 3D geometric meshes and point clouds. It is intended to improve the storage and transmission of 3D graphics.
Text to 3D generation in Apple Vision Pro built with the VisionOS SDK. 3D Scribblenauts in AR for the Scale Generative AI Hackathon. Won Scale AI Prize
Drools is a rule engine, DMN engine and complex event processing (CEP) engine for Java.
On-device AI across mobile, embedded and edge for PyTorch
Train your parkour robot in less than 20 hours.
Fact-checking LLM outputs with langchain
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Start a chat with any document with Ada Embedding and Davinci Completion
Fine-tune mistral-7B on 3090s, a100s, h100s
Code and model for the paper "Improving Language Understanding by Generative Pre-Training"
🔥 Turn entire websites into LLM-ready markdown
Fast and memory-efficient exact attention
Flax is a neural network library for JAX that is designed for flexibility.
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
Generative Agents: Interactive Simulacra of Human Behavior
glTF – Runtime 3D Asset Delivery
Google Research
Code for the paper "Language Models are Unsupervised Multitask Learners"
Dataset of GPT-2 outputs for research in detection, biases, and more
GPT-3: Language Models are Few-Shot Learners
Javascript BPE Encoder Decoder for GPT-2 / GPT-3
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
gpt4all: an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue
H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://h2oai.github.io/h2o-llmstudio/