Pinned Repositories
beavertails
BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
human-language-intelligence.github.io
A static GitHub Pages website that updates based on Google Drive documents.
kore
llama-recipes
Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger
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.
person2pix.py
ResponsibleNLP
Repository for research in the field of Responsible NLP at Meta.
Value_Analysis
VIM
kore
SwimmingChoi's Repositories
SwimmingChoi/Value_Analysis
SwimmingChoi/llama-recipes
Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger
SwimmingChoi/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.
SwimmingChoi/ResponsibleNLP
Repository for research in the field of Responsible NLP at Meta.
SwimmingChoi/beavertails
BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
SwimmingChoi/VIM
SwimmingChoi/human-language-intelligence.github.io
A static GitHub Pages website that updates based on Google Drive documents.
SwimmingChoi/kore
SwimmingChoi/person2pix.py