Official implementation for Diffusion Alignment as Sampling (DAS), ICLR'25, Spotlight

Rare-to-Frequent (R2F), ICLR'25, Spotlight

A Survey on Large Language Model-Based Game Agents

A cryptocurrency trading API with more than 100 exchanges in JavaScript / TypeScript / Python / C# / PHP / Go

Data used for ACL 2020 paper “None of the Above”:Measure Uncertainty in Dialog Response Retrieval

Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models

Robust Speech Recognition via Large-Scale Weak Supervision

Python wrapper for the arXiv API

Let's build better datasets, together!

Compress your input to ChatGPT or other LLMs, to let them process 2x more content and save 40% memory and GPU time.

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

MambaFormer in-context learning experiments and implementation for https://arxiv.org/abs/2402.04248

Grok open release

一个用于在 macOS 上平滑你的鼠标滚动效果或单独设置滚动方向的小工具, 让你的滚轮爽如触控板 | A lightweight tool used to smooth scrolling and set scroll direction independently for your mouse on macOS

(Obsolete) Archive of Rant 3.x.

Deep Learning Zero to All - Pytorch

The code of ACL 2020 paper "You Impress Me: Dialogue Generation via Mutual Persona Perception"

A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"

Retrieval and Retrieval-augmented LLMs

Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning

This repository contains the NarrativeQA dataset. It includes the list of documents with Wikipedia summaries, links to full stories, and questions and answers.

Official inference library for Mistral models

Spherical Merge Pytorch/HF format Language Models with minimal feature loss.

Tools for merging pretrained large language models.

Repo for the paper "Large Language Models Struggle to Learn Long-Tail Knowledge"

Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics

BookNLP, a natural language processing pipeline for books

Code for the paper "Language Models are Unsupervised Multitask Learners"

Code and model for the paper "Improving Language Understanding by Generative Pre-Training"