Roberta Python Packages

curated-transformers

🤖 A PyTorch library of curated Transformer models and their composable components

loralib

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

adaptive-classifier

A flexible, adaptive classification system for dynamic text classification

news-please

news-please - an integrated web crawler and information extractor for news that just works

bertviz

BertViz: Visualize Attention in Transformer Models

embedding-as-service

One-Stop Solution to encode sentence to fixed length vectors from various embedding techniques

bert-seq2seq

pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。

happytransformer

Happy Transformer makes it easy to fine-tune and perform inference with NLP Transformer models.

farm

:house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.

bert-seq2seq-ddp

bert_seq2seq的DDP版本，支持bert、roberta、nezha、t5、gpt2等模型，支持seq2seq、ner、关系抽取等任务，无需添加额外代码，轻松启动DDP多卡训练。

deberta

The implementation of DeBERTa

belt-nlp

BERT classification model for processing texts longer than 512 tokens. Text is first divided into smaller chunks and after feeding them to BERT, intermediate results are pooled. The implementation allows fine-tuning.

texar-pytorch

Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CASL project: http://casl-project.ai/

smaberta

Wrapper for stable version of RoBERTa language models

adamix-gpt2

PyTorch implementation of low-rank adaptation (LoRA) and Adamix, a parameter-efficient approach to adapt a large pre-trained deep learning model which obtains performance better than full fine-tuning.

embedding-as-service-client

One-Stop Solution to encode sentence to fixed length vectors from various embedding techniques

ernie

Simple State-of-the-Art BERT-Based Sentence Classification with Keras / TensorFlow 2. Built with HuggingFace's Transformers.

langformers

🚀 Unified NLP Pipelines for Language Models

nlp-lmd

Language Model Decomposition: Quantifying the Dependency and Correlation of Language Models

fastc

Unattended Lightweight Text Classifiers with LLM Embeddings

sam-lora-lib

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"