Shenghui Li's starred repositories
alpaca-lora
Instruct-tune LLaMA on consumer hardware
foundation-model-stack
🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.
fms-hf-tuning
🚀 Collection of tuning recipes with HuggingFace SFTTrainer and PyTorch FSDP.
LLaMA-Adapter
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
Visual-Adversarial-Examples-Jailbreak-Large-Language-Models
Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models
lm-evaluation-harness
A framework for few-shot evaluation of language models.
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
awesome-mixture-of-experts
A collection of AWESOME things about mixture-of-experts
jailbreakbench
An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]
ChatGPT_DAN
ChatGPT DAN, Jailbreaks prompt
LLMs-Finetuning-Safety
We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.
Phi-3CookBook
This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks.
Hands-on-RL
https://hrl.boyuai.com/