- Dublin, Ireland
- https://www.linkedin.com/in/anikalburgi/
- @anikalburgi
Stars
code and resources used in the Going Meta sessions
A Unified Library for Parameter-Efficient and Modular Transfer Learning
Q-Star Agent Code: A reinforcement learning-based framework for intelligent agents using Microsoft AutoGen. It leverages Q-Star, a Q-learning variant, for dynamic decision-making. Ideal for develop…
A Python client for the Neo4j Graph Data Science (GDS) library
An Object Graph Mapper (OGM) for the Neo4j graph database.
EOL! Py2neo is a comprehensive Neo4j driver library and toolkit for Python.
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.
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Training LLMs with QLoRA + FSDP
Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…
Unofficial TradingView technical analysis API wrapper.
📈 Get real-time stocks from TradingView
A Unified Toolkit for Deep Learning Based Document Image Analysis
Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
the AI-native open-source embedding database
Preprocessing pipeline notebooks and API supporting text extraction from SEC documents
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
A one stop repository for generative AI research updates, interview resources, notebooks and much more!
Recommending Diverse and Serendipitous Movies using Movielens Tag-Genome dataset
Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Easily embed, cluster and semantically label text datasets
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.