sbmaruf

jina

☁️ Build multimodal AI applications with cloud-native stack

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

PromptPapers

Must-read papers on prompt-based tuning for pre-trained language models.

GLM

GLM (General Language Model)

promptsource

Toolkit for creating, sharing and using natural language prompts.

cpu_features

A cross platform C99 library to get cpu features at runtime.

tsne-cuda

GPU Accelerated t-SNE for CUDA with Python bindings

TransCoder

Public release of the TransCoder research project https://arxiv.org/pdf/2006.03511.pdf

Megatron-DeepSpeed

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

NL-Augmenter

NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations

t-zero

Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)

ACL-anthology-corpus

This repository provides details and links to the ACL anthology corpus/collection including .bib, .pdf and grobid extractions of the pdfs

pptod

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System (ACL 2022)

deep-learning-models

Natural language processing & computer vision models optimized for AWS

LTP

[KDD'22] Learned Token Pruning for Transformers

LaplacianShot

Laplacian Regularized Few Shot Learning

multilingual-modeling

BLOOM+1: Adapting BLOOM model to support a new unseen language

tokenizer

Convert source code into numerical tokens

ml_nlp_paper_data

Dataset of ML and NLP papers

nq-open

carbon-footprint

A repository for `codecarbon` logs.

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

multilingual-t0

Multilingual extension of T0

LightOJ

upload-folder-google-drive

UXLA

We propose UXLA, a novel data augmentation framework for self-supervised learning in zero-resource transfer learning scenarios.

Multi-Codes

hexagonal-architecture

BIG-bench

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

eval_t0_deepspeed

Evaluate T0 with DeepSpeed