[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

A Data Streaming Library for Efficient Neural Network Training

🚀 Efficient implementations of state-of-the-art linear attention models

Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, implementing, and testing new search methods. Baguetter support…

MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks

Public repo for the NeurIPS 2023 paper "Unlimiformer: Long-Range Transformers with Unlimited Length Input"

Accessible large language models via k-bit quantization for PyTorch.

A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

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

PyTorch + HuggingFace code for RetoMaton: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022), including an implementation of kNN-LM and kNN-MT

Efficient, Low-Resource, Distributed transformer implementation based on BMTrain

Efficient Training (including pre-training and fine-tuning) for Big Models

Running large language models on a single GPU for throughput-oriented scenarios.

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Scalable training for dense retrieval models.

Model API for GALACTICA

[EMNLP 2022] Training Language Models with Memory Augmentation https://arxiv.org/abs/2205.12674

Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning

This repository provides details and links to the ACL anthology corpus/collection including .bib, .pdf and grobid extractions of the pdfs

Source code and dataset for EMNLP 2020 paper "MAVEN: A Massive General Domain Event Detection Dataset".

A latent text-to-image diffusion model

Official code and model checkpoints for our EMNLP 2022 paper "RankGen - Improving Text Generation with Large Ranking Models" (https://arxiv.org/abs/2205.09726).

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

The source code of our COLING'18 paper "Few-Shot Charge Prediction with Discriminative Legal Attributes".

The respository of jec-qa.

Open Chinese Language Pre-trained Model Zoo