justinphan3110

SciFive

SciFive: a text-text transformer model for biomedical literature

deepspeed_lora

Training LORA with Deepspeed for pretraining purpose

BioNERBERT

How Language Models teach Language Models to do NER in Biomedical Domain

Resume

My Resume typed with Latex

vietai-research-blog

VietAI Research Scientific Blog Frontend

alpaca-lora

Instruct-tune LLaMA on consumer hardware

auditing-llms

campuskvetch

complains a great deal about campus issue and we will fix it

CWRUPS

EECS341 Final Project

DeBERTa

The implementation of DeBERTa

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

DeepSpeedExamples

Example models using DeepSpeed

EECS397-Project

Projects for CWRU's EECS397:System Programming (Spring 2020)

efficient_alpaca

The aim of this repository is to utilize LLaMA to reproduce and enhance the Stanford Alpaca

ensemble_trl

FastChat

The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

gec_with_backtrans

Grammatical Error Correction (GEC) with Back Translation

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

justinphan3110

justinphan3110.github.io

lm-evaluation-harness

A framework for few-shot evaluation of language models.

loconotion

📄 Python tool to turn Notion.so pages into lightweight, customizable static websites

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Prompt-Engineering-Guide

:octopus: Guides, papers, lecture, and resources for prompt engineering

representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

test

Measuring Massive Multitask Language Understanding | ICLR 2021

TextGrad

tianshou

An elegant PyTorch deep reinforcement learning library.

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)