exowanderer

ryoma

Common AI agent framework solving your data problems

cv

My CV

buffer-of-thought-llm

[NeurIPS 2024 Spotlight] Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models

barebone-rag

Wikimedia Hackathon 2024 Tallinn, Semantic Search and RAG on a FOSS stack

ROCm

AMD ROCm™ Software - GitHub Home

vector-index-visualization-tool

visualization tool for vector search index

PyTorch-BigGraph

Generate embeddings from large-scale graph-structured data.

biggraph-wikidata-search-with-weaviate

Search through Facebook Research's PyTorch BigGraph Wikidata-dataset with the Weaviate vector search engine

megalodon

Reference implementation of Megalodon 7B model

QAnything

Question and Answer based on Anything.

instructor

structured outputs for llms

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

DSen2

Super-Resolution of Sentinel-2 Images: Learning a Globally Applicable Deep Neural Network

biometricDashboard3

Real-time biometric visualizer.

YouTube-Blog

Codes to complement YouTube videos and blog posts on Medium.

devika

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

lakblogs

Code and notebooks associated with my blogposts

DeepRAGTuner

End to End fine tuning for RAG models using PyTorch Lightning, Hydra, W&B and MosaicML Streaming

RAGTune

Tuning and Evaluation of RAG pipeline. (Automated optimization to be added soon)

auto-dev

🧙‍AutoDev: The AI-powered coding wizard（AI 驱动编程助手） with multilingual support 🌐, auto code generation 🏗️, and a helpful bug-slaying assistant 🐞! Customizable prompts 🎨 and a magic Auto Dev/Testing/Document/Agent feature 🧪 included! 🚀

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

Time-LLM

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

FlopPITy

Normalizing Flow Exoplanet Parameter Inference Toolkyt

vision_transformers_explained

This folder of code contains code and notebooks to supplement the "Vision Transformers Explained" series published on Towards Data Science written by Skylar Callis.

sdxl-koala

[NeurIPS 2024] Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis

p_tqdm

Parallel processing with progress bars

lab

time-series-analysis

Collection of notebooks for time series analysis

lag-llama

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

RAGatouille

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.