roysh's repositories
100daysofComputerVision
This is a collection of projects done for 100 days of computer vision
awesome-cheap-llms
Cost reduction tools and techniques for LLM based systems
chronos-forecasting
Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting
codel
✨ Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor.
CTGAN
Conditional GAN for generating synthetic tabular data.
dbrx
Code examples and resources for DBRX, a large language model developed by Databricks
evolutionary-model-merge
Official repository of Evolutionary Optimization of Model Merging Recipes
explainerdashboard
Quickly build Explainable AI dashboards that show the inner workings of so-called "blackbox" machine learning models.
faiss
A library for efficient similarity search and clustering of dense vectors.
Getting-Started-with-Generative-AI
A curated list of articles and tutorials to start with and understand generative AI
GPTFast
Accelerate your Hugging Face Transformers 6-8.5x. Native to Hugging Face and PyTorch.
groundingLMM
Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks [CVPR 2024].
hqq
Official implementation of Half-Quadratic Quantization (HQQ)
LLaMA-Factory
Unify Efficient Fine-tuning of 100+ LLMs
llm-zoomcamp
LLM Zoomcamp - a free online course about building an AI bot that can answer questions about your knowledge base
llm.c
LLM training in simple, raw C/CUDA
mace
MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.
milvus
A cloud-native vector database, storage for next generation AI applications
MONAI
AI Toolkit for Healthcare Imaging
nextflow
A DSL for data-driven computational pipelines
polkadot-introspector
A collection of tools focused on debugging and monitoring the relay chain and parachain progress from a 🐦-view
polkadot-js-tools
Various cli tools for Polkadot and Substrate chains, including basic node monitoring, making API queries via a cli app and other command-line tools
pydicom
Read, modify and write DICOM files with python code
SALT
Softmax for Arbitrary Label Trees (SALT) is a framework for training segmentation networks using conditional probabilities to model hierarchical relationships in the data.
transformer-heads
Toolkit for attaching, training, saving and loading of new heads for transformer models
vscode-python-medium
Medium Article Supporting Code