gaotianyu1350

stable-diffusion

A latent text-to-image diffusion model

stanford_alpaca

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

ParlAI

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

FlexGen

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

MiniCPM

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

metaseq

Repo for external large-scale work

bitsandbytes

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

galai

Model API for GALACTICA

smoothquant

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

unlimiformer

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

rank_bm25

A Collection of BM25 Algorithms in Python

OpenDelta

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

OpenCLaP

Open Chinese Language Pre-trained Model Zoo

contriever

Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning

BMTrain

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

LegalPapers

Must-read Papers on Legal Intelligence

incoder

Generative model for code infilling and synthesis

knn-transformers

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

dpr-scale

Scalable training for dense retrieval models.

ModelCenter

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

TRIME

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

LegalPLMs

Source code and checkpoints for legal pre-trained language models.

ACL-anthology-corpus

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

MAVEN-dataset

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

rankgen

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

attribute_charge

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

TopJudge

CLAIM

jec-qa

The respository of jec-qa.

QAJudge