# ymcui/Chinese-XLNet

Pre-Trained Chinese XLNet（中文XLNet预训练模型）

Repository: https://github.com/ymcui/Chinese-XLNet
Canonical: https://ross.abutalabs.com/products/chinese-xlnet
Homepage: http://xlnet.hfl-rc.com
Language: Python
License: Apache-2.0
License Family: permissive
Topics: natural-language-processing, xlnet, tensorflow, pytorch, nlp
Last push: 2026-04-19T01:00:14+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 78, release rhythm 35, longevity 100
- inputs: {"age_days": 2606, "days_push": 137, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1646, forks 278 (observed 2026-08-28T04:05:16.386356+00:00)

## What it is
A repository of pre-trained Chinese XLNet language models (XLNet-base and XLNet-mid) released by HFL, available in PyTorch and TensorFlow formats via Hugging Face Transformers. It provides model weights, fine-tuning details, and baseline results for Chinese NLP tasks.

## Use cases
- download a pretrained Chinese XLNet model
- fine-tune XLNet on Chinese text classification
- use Chinese XLNet with Hugging Face transformers
- get Chinese pretrained model weights for NER
- compare Chinese XLNet baselines on NLP tasks

## When to choose
- you need a Chinese XLNet checkpoint for fine-tuning or research
- you want PyTorch or TensorFlow weights compatible with the transformers library

## When to avoid
- you need a modern LLM or instruction-tuned model rather than an encoder-style pretrained model
- you work with languages other than Chinese

## Facets
- artifact type: dataset
- maturity: maintenance
- function: machine-learning, nlp
- domain: large-language-models, machine-learning
- platform: python
- tags: pretrained-models, chinese-nlp, xlnet, transformers, huggingface, natural-language-processing, tensorflow, gpu

## Member repositories
- ymcui/Chinese-XLNet (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:16.386356+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:45:24.256631+00:00, confidence not recorded.
  - readme: https://github.com/ymcui/Chinese-XLNet (fetched 2026-08-28T04:05:16.386356+00:00, sha 77a0821fdc22)
- Data as of 2026-08-30T08:39:29.467469+00:00.