wxjiao Goto Github PK

llm-shearing

Preprint: Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

llmspeculativesampling

Fast inference from large lauguage models via speculative decoding

lmflow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

loss-landscape

Code for visualizing the loss landscape of neural nets

loss-landscapes

Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch

mamba

mass

MASS: Masked Sequence to Sequence Pre-training for Language Generation

mediawiki

MediaWiki API wrapper in python http://pymediawiki.readthedocs.io/en/latest/

mt-reading-list

A machine translation reading list maintained by Tsinghua Natural Language Processing Group

multidds

Code for the paper "Balancing Training for Multilingual Neural Machine Translation, ACL 2020"

multilingualsift

MultilingualSIFT: Multilingual Supervised Instruction Fine-tuning

multimodal-feature-extraction

A detailed description on how to extract and align text, audio, and video features at word-level.

noisy-text

Add noise to your text, can be used to improve synthetic training corpus for Neural Machine Translation

opencc

Conversion between Traditional and Simplified Chinese

opensubtitles-parser

download, extract, parse and tokenize the opensubtitles dataset with this script

parrot

The ParroT framework to enhance and regulate the Translation Abilities during Chat based on open-sourced LLMs (e.g., LLaMA-7b, Bloomz-7b1-mt) and human written translation and evaluation data.

phramer

pre-code

Implementation of our paper "Exploiting Unsupervised Data for Emotion Recognition in Conversations" in the Findings of EMNLP-2020.

proxy-settings

Notes of proxy settings for conda, pip, python scripts.

pychatgpt

⚡️ Python client for the unofficial ChatGPT API with auto token regeneration, conversation tracking, proxy support and more.

resnet-video-features

Temporal video features extracted from ImageNet pre-trained ResNet-152.

ribes

RIBES is an automatic evaluation metric for machine translation.

rulm

Language modeling and instruction tuning for Russian

self-training-text-generation

Implementation of ICLR 2020 paper "Revisiting Self-Training for Neural Sequence Generation"

sent-summary

spacy-langdetect

A fully customisable language detection pipeline for spaCy

staged-training

Staged Training for Transformer Language Models

stopwords-iso

All languages stopwords collection

svcca

text_classification

all kinds of text classificaiton models and more with deep learning