206 Open source projects that are alternatives of or similar to Black-Box-Tuning

The source code of "Language Models are Few-shot Multilingual Learners" (MRL @ EMNLP 2021)

Dasher text entry in HTML, CSS, JavaScript, and SVG

Character-aware Neural Language Model implemented by PyTorch

KB국민은행에서 제공하는 경제/금융 도메인에 특화된 한국어 ALBERT 모델

Source codes for "Improved Few-Shot Visual Classification" (CVPR 2020), "Enhancing Few-Shot Image Classification with Unlabelled Examples" (WACV 2022), and "Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning" (Neural Networks 2022 - in submission)

Enhancing the BERT training with Semi-supervised Generative Adversarial Networks

Few-shot Keyword Spotting in Any Language and Multilingual Spoken Word Corpus

A minimal TF2 re-implementation of the OpenAI GPT training

(ECCV 2020) PyTorch implementation of paper "Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild"

LibFewShot: A Comprehensive Library for Few-shot Learning.

A toolkit for neural language modeling using Tensorflow including basic models like RNNs and LSTMs as well as more advanced models.

PyTorch code for NeurIPSW 2020 paper (4th Workshop on Meta-Learning) "Few-Shot Unsupervised Continual Learning through Meta-Examples"

machine learning

[CVPR 2021] Few-shot 3D Point Cloud Semantic Segmentation

Code for the ICLR 2021 paper "A Distributional Approach to Controlled Text Generation"

Learning To Compare For Text , Few shot learning in text classification

Code and data of ACL 2021 paper "Few-NERD: A Few-shot Named Entity Recognition Dataset"

24-hour Automatic Speech Recognition

COLING'2020: CoLAKE: Contextualized Language and Knowledge Embedding

Language Modeling and Text Classification in Malayalam Language using ULMFiT

ACL 2019 paper:Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification

Code for ACL'19 "Few-Shot Representation Learning for Out-Of-Vocabulary Words"

Presenting Collection of Pretrained Models. Links to pretrained models in NLP and voice.

📃Language Model based sentences scoring library

A black-box optimization benchmark tool

finetune bert for small dataset text classification in a few-shot learning manner using ProtoNet

Sinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms. The SLA algorithm is described in full in this ICML 2021 paper: https://arxiv.org/abs/2102.08622.

LSTM Language Model with Subword Units Input Representations

GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

Chinese Natural Language Correction via Language Model

Dialogue Knowledge Transfer Networks (DiKTNet)

Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.

Experiments for automated personality detection using Language Models and psycholinguistic features on various famous personality datasets including the Essays dataset (Big-Five)

Code Generation as a Dual Task of Code Summarization.

Context Aware Language Models

[ACL‘20] Highway Transformer: A Gated Transformer.

awesome few shot / meta learning papers

Personalized Query Completion

A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.

A GPT, made only of MLPs, in Jax

PyTorch implementation of 'Squeeze and Excite' Guided Few Shot Segmentation of Volumetric Scans

An open source implementation of CLIP.

Awesome Few-shot learning

Pytorch implementation of a basic language model using Attention in LSTM network

RNN(LSTM, GRU) in Theano with mini-batch training; character-level language models in Theano

Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

🏭 PDF text extraction pipeline: self-hosted, local-first, Docker-based

Laplacian Regularized Few Shot Learning

[NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining

API for the GPT-J language model 🦜. Including a FastAPI backend and a streamlit frontend

📄 Spatial Contrastive Learning for Few-Shot Classification (ECML/PKDD 2021).

SWIG Wrapper for the SRILM toolkit

Official code of our work, Unified Pre-training for Program Understanding and Generation [NAACL 2021].

A non-official 100% PyTorch implementation of META-DATASET benchmark for few-shot classification

Kaldi-based Korean ASR (한국어 음성인식) open-source project

Code of Empirical Bayes Transductive Meta-Learning with Synthetic Gradients

Curated list of all NLP Resources

Useful resources for Mongolian NLP

a deep recurrent model for exchangeable data

This repo is the home of Romanian Transformers.