QLoRA: Efficient Finetuning of Quantized LLMs

Single-document unsupervised keyword extraction

The code of our paper "SIFRank: A New Baseline for Unsupervised Keyphrase Extraction Based on Pre-trained Language Model"

This is code for paper: MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction

Code for paper "Incorporating Multimodal Information in Open-Domain Web Keyphrase Extraction"

Data for ArXiv 2024 paper "Large Language Models as Zero-Shot Keyphrase Extractors: A Preliminary Empirical Study".

Code for NAACL 2022 paper "Hyperbolic Relevance Matching for Neural Keyphrase Extraction".

Enhanced ChatGPT Clone: Features Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, langchain, D…

Inference code for Llama models

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Easy Docker setup for Stable Diffusion with user-friendly UI

CTF challenges designed and implemented in machine learning applications

Docker image for building C++ applications with OpenCV.

Reverse engineered ChatGPT API

Code and documentation to train Stanford's Alpaca models, and generate the data.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more