cytan17726

arxiv_crawler

这是一个高效，快捷的arXiv论文爬虫，它可以将指定时间范围，指定主题，包含指定关键词的论文信息爬取到本地，并且将其中的标题和摘要翻译成中文。

knowledge-of-knowledge

learning-to-refuse

Official Implementation of "Learning to Refuse: Towards Mitigating Privacy Risks in LLMs"

Say-I-Dont-Know

[ICML'2024] Can AI Assistants Know What They Don't Know?

LLaMA-Factory

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

probing-lm-data

Official Implementation of "Probing Language Models for Pre-training Data Detection"

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

UHGEval

[ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA

MoE-SFT

🍼 Official implementation of Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts

HALOs

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

mink-plus-plus

Min-K%++: Improved baseline for detecting pre-training data of LLMs https://arxiv.org/abs/2404.02936

lm-evaluation-harness

A framework for few-shot evaluation of language models.

TruthX

Code for ACL 2024 paper "TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space"

Awesome-LLM-Safety

A curated list of safety-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights into the safety implications, challenges, and advancements surrounding these powerful models.

llm-hallucination-survey

Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"

DCR-consistency

DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and Improvement of Large Language Models

llama-moe

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

TruthfulQA

TruthfulQA: Measuring How Models Imitate Human Falsehoods

UnknownBench

Repo for paper: Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge

FalseQA

Repo for ACL2023 paper "Won't Get Fooled Again: Answering Questions with False Premises"

R-Tuning

[NAACL 2024 Outstanding Paper] Source code for the NAACL 2024 paper entitled "R-Tuning: Instructing Large Language Models to Say 'I Don't Know'"

SelfAware

Do Large Language Models Know What They Don’t Know?

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

Mirror

🪞A powerful toolkit for almost all the Information Extraction tasks.

Pangu

Code for reproducing the ACL'23 paper: Don't Generate, Discriminate: A Proposal for Grounding Language Models to Real-World Environments

Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

beam_retriever

[NAACL 2024] End-to-End Beam Retrieval for Multi-Hop Question Answering

api-for-open-llm

Openai style api for open large language models, using LLMs just as chatgpt! Support for LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, Xverse, SqlCoder, CodeLLaMA, ChatGLM, ChatGLM2, ChatGLM3 etc. 开源大模型的统一后端接口

CMMLU

CMMLU: Measuring massive multitask language understanding in Chinese

server-remote-control

Remote power control by accessing BMI.