liujuncn Goto Github PK

mega-image

Implementation of Mega on Image Classification

ml-pretrained

Implementations of various pre-trained models

mobilesam

This is the offiicial code for Faster Segment Anything (MobileSAM) project that makes SAM lightweight

mods

moss

An open-source tool-augmented conversational language model from Fudan University

mt3

MT3: Multi-Task Multitrack Music Transcription

mteb

MTEB: Massive Text Embedding Benchmark

muse-maskgit-pytorch

Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch

naturalspeech

A fully working pytorch implementation of NaturalSpeech (Tan et al., 2022)

nbce

Naive Bayes-based Context Extension

nemo

NeMo: a toolkit for conversational AI

neurox

A Python library that encapsulates various methods for neuron interpretation and analysis in Deep NLP models.

nlp_hacks_mirostat

ocropus4inf

odex

Execution-Based Evaluation for Open Domain Code Generation

open-instruct

open-llms

🤖 A list of open LLMs available for commercial use.

open-muse

Open reproduction of MUSE for fast text2image generation.

openai-python

The OpenAI Python library provides convenient access to the OpenAI API from applications written in the Python language.

openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

opro

official code for "Large Language Models as Optimizers"

paddlenlp

👑 Easy-to-use and powerful NLP library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis and 🖼 Diffusion AIGC system etc.

paint-by-example

Paint by Example: Exemplar-based Image Editing with Diffusion Models

paintmind

Fast and controllable text-to-image model.

palm-rlhf-pytorch

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

patchtst

An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730

pdfplumber

Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.

pgcontents

A Postgres-backed ContentsManager implementation for Jupyter

phd-lab

Experimentor based on delve-deep-dive

poetry

汉语现代诗歌语料库整理，3489诗人，81.7K诗歌，15.43M字。持续扩充...