Duy V. Phung's starred repositories

chameleon

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

Language:PythonLicense:NOASSERTIONStargazers:1163Issues:0Issues:0
Language:PythonStargazers:320Issues:0Issues:0

schedule_free

Schedule-Free Optimization in PyTorch

Language:PythonLicense:Apache-2.0Stargazers:1519Issues:0Issues:0

LLM_Tree_Search

(ICML 2024) Alphazero-like Tree-Search can guide large language model decoding and training

Language:PythonStargazers:127Issues:0Issues:0

TPU-Alignment

Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:203Issues:0Issues:0

MuseTalk

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

Language:PythonLicense:NOASSERTIONStargazers:1706Issues:0Issues:0

MetaGPT

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Language:PythonLicense:MITStargazers:41102Issues:0Issues:0

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Language:PythonLicense:BSD-3-ClauseStargazers:5302Issues:0Issues:0

screenshot-to-code

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

Language:PythonLicense:MITStargazers:53885Issues:0Issues:0
Language:MathematicaStargazers:643Issues:0Issues:0

ml-engineering

Machine Learning Engineering Open Book

Language:PythonLicense:CC-BY-SA-4.0Stargazers:10106Issues:0Issues:0

Kaggle-Jane-Street-AE-MLP-xgb-TOP1

1th: Kaggle Jane Street Market Prediction: AE MLP+xgb

Language:Jupyter NotebookLicense:MITStargazers:29Issues:0Issues:0

animatediff-cli-prompt-travel

animatediff prompt travel

Language:PythonLicense:Apache-2.0Stargazers:1164Issues:0Issues:0

Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Language:PythonLicense:Apache-2.0Stargazers:12220Issues:0Issues:0

kani

kani (カニ) is a highly hackable microframework for chat-based language models with tool use/function calling. (NLP-OSS @ EMNLP 2023)

Language:PythonLicense:MITStargazers:536Issues:0Issues:0

lm-human-preference-details

RLHF implementation details of OAI's 2019 codebase

Language:PythonLicense:MITStargazers:135Issues:0Issues:0

VALL-E-X

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io

Language:PythonLicense:MITStargazers:7378Issues:0Issues:0
Language:PythonLicense:MITStargazers:192Issues:0Issues:0

voice-changer

リアルタイムボイスチェンジャー Realtime Voice Changer

Language:PythonLicense:NOASSERTIONStargazers:15145Issues:0Issues:0

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Language:PythonLicense:NOASSERTIONStargazers:79735Issues:0Issues:0

vall-e

An unofficial PyTorch implementation of the audio LM VALL-E

Language:PythonLicense:MITStargazers:2904Issues:0Issues:0

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

Language:PythonLicense:MITStargazers:37260Issues:0Issues:0

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

Language:PythonLicense:MITStargazers:63436Issues:0Issues:0
Language:PythonLicense:Apache-2.0Stargazers:2559Issues:0Issues:0

trlx

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

Language:PythonLicense:MITStargazers:4379Issues:0Issues:0

stable-diffusion

A latent text-to-image diffusion model

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:66335Issues:0Issues:0

EquiBind

EquiBind: geometric deep learning for fast predictions of the 3D structure in which a small molecule binds to a protein

Language:PythonLicense:MITStargazers:464Issues:0Issues:0

CodeT5

Home of CodeT5: Open Code LLMs for Code Understanding and Generation

Language:PythonLicense:BSD-3-ClauseStargazers:2647Issues:0Issues:0

naturalcc

NaturalCC: An Open-Source Toolkit for Code Intelligence

Language:PythonLicense:MITStargazers:248Issues:0Issues:0

Multi-Type-TD-TSR

Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition:

Language:Jupyter NotebookLicense:MITStargazers:249Issues:0Issues:0