chiennv2000

followers

following

stars

University of Oregon

Oregon, USA

https://chiennv2000.github.io/

Chien Nguyen's starred repositories

build-your-own-x

Master programming by recreating your favorite technologies from scratch.

representation-engineering

Representation Engineering: A Top-Down Approach to AI Transparency

Language:Jupyter NotebookMIT59700

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

Language:PythonApache-2.02364400

streaming

A Data Streaming Library for Efficient Neural Network Training

Language:PythonApache-2.097800

composer

Supercharge Your Model Training

Language:PythonApache-2.0504400

hallucination-leaderboard

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

Apache-2.0108000

LLM-Workshop

LLM Workshop by Sourab Mangrulkar

Language:Jupyter NotebookApache-2.028400

bigscience

Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.

Language:ShellNOASSERTION95200

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Language:PythonNOASSERTION125900

PASTA

PASTA: Post-hoc Attention Steering for LLMs

Language:PythonMIT8500

consistencydecoder

Consistency Distilled Diff VAE

Language:PythonMIT208200

CTranslate2

Fast inference engine for Transformer models

Language:C++MIT292700

OpenELM

Evolution Through Large Models

Language:PythonMIT65500

mmengine

OpenMMLab Foundational Library for Training Deep Learning Models

Language:PythonApache-2.0106800

determined

Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. Works with PyTorch and TensorFlow.

Language:GoApache-2.0289100

DeepSpeed

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

Language:PythonApache-2.03323700

natural-instructions

Expanding natural instructions

Language:PythonApache-2.091200

DecT

Source code for ACL 2023 paper Decoder Tuning: Efﬁcient Language Understanding as Decoding

Language:PythonMIT4500

ModelCenter

Efficient, Low-Resource, Distributed transformer implementation based on BMTrain

Language:PythonApache-2.021800

BMTrain

Efficient Training (including pre-training and fine-tuning) for Big Models

Language:PythonApache-2.052100

alignment-handbook

Robust recipes to align language models with human and AI preferences

Language:PythonApache-2.0404600

intel-extension-for-transformers

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

Language:PythonApache-2.0199900

FewDocAE

Few-Shot Document-Level Event Argument Extraction: https://arxiv.org/abs/2209.02203

Language:PythonGPL-3.01100

self-rag

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

Language:PythonMIT153000

chat-ui

Open source codebase powering the HuggingChat app

Language:TypeScriptApache-2.0653300

M3rlin-fmengine

M3 Training Using FMengine

Language:PythonApache-2.0200

DoLa

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

Language:Python35400

HojiChar

The robust text processing pipeline framework enabling customizable, efficient, and metric-logged text preprocessing.

Language:PythonApache-2.011000

freshqa

Data and code for FreshLLMs (https://arxiv.org/abs/2310.03214)

Language:Jupyter NotebookApache-2.028800

ColossalAI

Making large AI models cheaper, faster and more accessible

Language:PythonApache-2.03811400