jack57lee

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

uniem

unified embedding model

Llama-Chinese

Llama中文社区，Llama3在线体验和微调模型已开放，实时汇总最新Llama3学习资料，已将所有代码更新适配Llama3，构建最好的中文Llama大模型，完全开源可商用

Megatron-LLaMA

Best practice for training LLaMA models in Megatron-LM

Megatron-LLM

distributed trainer for LLMs

ColossalAI

Making large AI models cheaper, faster and more accessible

Fengshenbang-LM

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

BMTools

Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins

ToolBench

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

ChatGLM-Efficient-Tuning

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

DIGAT

DIGAT: Modeling News Recommendation with Dual-Graph Interaction

P-tuning-v2

An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

OpenPrompt

An Open-Source Framework for Prompt-Learning.

OTT-QA

Code and Data for ICLR2021 Paper "Open Question Answering over Tables and Text"

IMRec

The dataset for paper "Why Do We Click: Visual Impression-aware News Recommendation", ACM MM 2021

DRhard

SIGIR'21: Optimizing DR with hard negatives and achieving SOTA first-stage retrieval performance on TREC DL Track.

neural-ranking-kd

Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation

FiD

Fusion-in-Decoder

news-recommendation

Implementations of some methods in news recommendation.

PLM4NewsRec

PAQ

Code and data to support the paper "PAQ 65 Million Probably-Asked Questions andWhat You Can Do With Them"

tapas

End-to-end neural table-text understanding models.

recommenders

Best Practices on Recommendation Systems

DensePhrases

[ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too https://arxiv.org/abs/2012.12624

pyserini

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

Lihang

Statistical learning methods, 统计学习方法(第2版)[李航] [笔记, 代码, notebook, 参考文献, Errata, lihang]

language

Shared repository for open-sourced projects from the Google AI Language team.

google-research

Google Research

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training