#90 · Primary category: NLP Tools & Text Processing
transformers_tasks
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
Project last updated:09/29/23
GitHub Stars
2.4K
Forks
398
Contributors
3
License
Other
Why we included this project
This repo is a code-first collection of NLP task implementations built on the Hugging Face transformers library. Instead of explaining algorithms in the abstract, it gives you runnable training scripts for text classification, generation, matching, named entity recognition, and relation extraction, with approaches like DSSM, Sentence-BERT, SimCSE, UIE, PET, and p-tuning wired up and ready to point at your own data through shell scripts and notebooks. It also covers the alignment side of the stack, including reward-model training and PPO for RLHF, ChatGLM fine-tuning, and zero-shot prompting, which helps when you move past single tasks into more advanced work. The task-based layout with clear entry points makes it a reasonable learning path for engineers new to transformers and a starting skeleton for experiments. The main caveat is that it is a work in progress, so treat each module as a baseline to verify and extend rather than a finished product.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
compromise
modest natural-language processing
tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
CoreNLP
CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.
Chinese-Word-Vectors
100+ Chinese Word Vectors 上百种预训练中文词向量