Xianjun-Yang

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

LLaMA-Factory

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

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

ml-engineering

Machine Learning Engineering Open Book

LWM

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

PurpleLlama

Set of tools to assess and improve LLM security.

weak-to-strong

magicoder

[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct

Awesome-Video-Diffusion-Models

[CSUR] A Survey on Video Diffusion Models

papermage

library supporting NLP and CV research on scientific papers

edm2

Analyzing and Improving the Training Dynamics of Diffusion Models (EDM2)

chat_templates

Chat Templates for 🤗 HuggingFace Large Language Models

HarmBench

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Awesome_papers_on_LLMs_detection

The lastest paper about detection of LLM-generated text and code

jailbreakbench

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]

llm-adaptive-attacks

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]

gemini-benchmark

research-career-tools

llm_unlearn

LLM Unlearning

wmdp

WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM performance on WMDP while retaining general capabilities.

weak-to-strong

Weak-to-Strong Jailbreaking on Large Language Models

pal

PAL: Proxy-Guided Black-Box Attack on Large Language Models

code-autodan

An unofficial implementation of AutoDAN attack on LLMs (arXiv:2310.15140)

Bonsai

Code for "Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes"

TrustAgent

TrustAgent: Towards Safe and Trustworthy LLM-based Agents

watermark-learnability

OverKill