RUCAIBox/TextBox

Health v2 · maintenance only

Adoption not part of the score

1097 stars · 115 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

TextBox 2.0 is a Python/PyTorch library providing a unified pipeline for applying pre-trained language models to text generation tasks. It bundles 13 generation tasks, 83 datasets, and 47 pre-trained models with training strategies like distributed data parallel.

Use cases

• benchmark pretrained language models on text generation tasks
• fine-tune seq2seq models for translation or summarization
• run story generation or style transfer experiments
• reproduce published text generation results
• train models with distributed data parallel on multiple GPUs
• evaluate generation quality with standard metrics

When to choose

• you need a standardized framework to compare many PLMs across generation tasks
• you want ready access to 83 benchmark datasets and 47 models
• you are doing NLP research on text generation and need reproducible pipelines

When to avoid

• you need production text generation serving rather than research experimentation
• you want the latest actively developed tooling - the last release was mid-2023
• you need a lightweight solution - installation pulls a modified transformers and extra dependencies

Facets

library · maturity maintenance

machine-learning nlp llm-training benchmarking deep-learning large-language-models python text-generation pytorch pretrained-language-models seq2seq natural-language-generation research-framework natural-language-processing linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="RUCAIBox/TextBox")