lynnalis's starred repositories
llama_index
LlamaIndex is a data framework for your LLM applications
Transformers-Tutorials
This repository contains demos I made with the Transformers library by HuggingFace.
deep-learning-coursera
Deep Learning Specialization by Andrew Ng on Coursera.
pdfplumber
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.
LLMDataHub
A quick guide (especially) for trending instruction finetuning datasets
ctransformers
Python bindings for the Transformer models implemented in C/C++ using GGML library.
semantic-router
Superfast AI decision making and intelligent processing of multi-modal data.
continual-learning
PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.
infiniteGPT
InfiniteGPT is a Python script that lets you input an unlimited size text into the OpenAI API. No more tedious copy & pasting. Long live multithreading!
DocumentLayoutAnalysis
Document Layout Analysis resources repos for development with PdfPig.
DocProduct
Medical Q&A with Deep Language Models
continual-learning-papers
Continual Learning papers list, curated by ContinualAI
coursera-natural-language-processing-specialization
Programming assignments from all courses in the Coursera Natural Language Processing Specialization offered by deeplearning.ai.
lightspeedGPT
Use GPT4 and GPT3.5 on inputs of unlimited size. Uses multithreading to process multiple chunks in parallel. Useful for tasks like Named Entity Recognition, information extraction on large books, datasets, etc.
language-models
pre-trained Language Models
llm_benchmarks
A collection of benchmarks and datasets for evaluating LLM.
gpt-tokens
Calculate the token consumption and amount of openai gpt message
routerbench
The code for the paper ROUTERBENCH: A Benchmark for Multi-LLM Routing System
vehicle-trajectory-prediction
Behavior Prediction in Autonomous Driving
DiverseEvol
Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning
gpt2-bert-medical-qa-chat
Medical domain-focused GPT-2 fine-tuning, optimization, and lightweighting research repository (compared to GPT-4).
Active-Object-Localization-Deep-Reinforcement-Learning
Active object localization ( bounding boxes ) using deep reinforcement learning.
NLPSpecialization
This repo contains the assignment and quiz solutions of Natural Language Processing Specialization, offered on Coursera.
Deep-Learning-Specialization-Coursera
:mortar_board: Deep Learning Specialization by Andrew Ng on Coursera.