-
Uppsala University
- Sweden
-
15:00
(UTC +02:00) - https://lishenghui.github.io/
Highlights
- Pro
Stars
Instruct-tune LLaMA on consumer hardware
🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.
The official GitHub page for the survey paper "Foundation Models for Music: A Survey".
🚀 Collection of tuning recipes with HuggingFace SFTTrainer and PyTorch FSDP.
Deep and online learning with spiking neural networks in Python
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
Improved techniques for optimization-based jailbreaking on large language models
Official repository for Towards Multi-modal Transformers in Federated Learning (ECCV2024)
Run PyTorch LLMs locally on servers, desktop and mobile
Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models
A high-throughput and memory-efficient inference and serving engine for LLMs
The Open Flash Library for creative expression on the web, desktop, mobile and consoles.
A framework for few-shot evaluation of language models.
Code and documentation to train Stanford's Alpaca models, and generate the data.
A collection of AWESOME things about mixture-of-experts
An official implementation of "FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model", which has been accepted by KDD'24.
An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
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.
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) avai…
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]