Stars
Continual Learning of Large Language Models: A Comprehensive Survey
An awesome repository & A comprehensive survey on interpretability of LLM attention heads.
A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..
Crawl a site to generate knowledge files to create your own custom GPT from a URL
The Open Cookbook for Top-Tier Code Large Language Model
👨💻 An awesome and curated list of best code-LLM for research.
[TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.
Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"
awesome papers in LLM interpretability
Must-read Papers on Knowledge Editing for Large Language Models.
Get your documents ready for gen AI
This paper list focuses on the theoretical and empirical analysis of language models, especially large language models (LLMs). The papers in this list investigate the learning behavior, generalizat…
An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI
Lottery Tickets in Evolutionary Optimization (Lange & Sprekeler, ICML 2023)
OCR & Document Extraction using vision models
Pytorch implementation of our paper accepted by TPAMI 2023 — Lottery Jackpots Exist in Pre-trained Models
A curated list of papers of interesting empirical study and insight on deep learning. Continually updating...
A curated list of Large Language Model (LLM) Interpretability resources.
📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥
Deploy high-performance AI models and inference pipelines on FastAPI with built-in batching, streaming and more.
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
Math OCR model that outputs LaTeX and markdown
All graph/GNN papers accepted at the International Conference on Machine Learning (ICML) 2024.
A repository in preparation for open-sourcing lottery ticket hypothesis code.