ShengYun (Anthony) Peng's starred repositories
openai-python
The official Python library for the OpenAI API
streaming-llm
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
Awesome-Multimodal-Large-Language-Models
:sparkles::sparkles:Latest Advances on Multimodal Large Language Models
sentence-transformers
Multilingual Sentence & Image Embeddings with BERT
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
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.
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.
open-parse
Improved file parsing for LLM’s
llm-attacks
Universal and Transferable Attacks on Aligned Language Models
loss-landscape
Code for visualizing the loss landscape of neural nets
how-do-vits-work
(ICLR 2022 Spotlight) Official PyTorch implementation of "How Do Vision Transformers Work?"
llm-self-defense
LLM Self Defense: By Self Examination, LLMs know they are being tricked
Machine-Learning-From-Scratch
Implementation of popular ML algorithms from scratch
PurpleLlama
Set of tools to assess and improve LLM security.