--- title: "UER-py vs awesome-pretrained-chinese-nlp-models" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/dbiir-uer-py-vs-lonepatient-awesome-pretrained-chinese-nlp-models" tools: ["dbiir-uer-py", "lonepatient-awesome-pretrained-chinese-nlp-models"] --- # UER-py vs awesome-pretrained-chinese-nlp-models *GraphCanon updated Aug 23, 2026* ## Verdict Pick UER-py if uER-py, an open-source PyTorch framework with a diverse model zoo for training and fine-tuning language models; pick awesome-pretrained-chinese-nlp-models if a comprehensive collection of advanced Chinese NLP models including large language models and multimodal setups. [UER-py](https://github.com/dbiir/UER-py/wiki) reports 3.1k GitHub stars, 520 forks, and 136 open issues, last pushed May 9, 2024. [awesome-pretrained-chinese-nlp-models](https://github.com/lonePatient/awesome-pretrained-chinese-nlp-models) has 5.6k stars, 514 forks, and 6 open issues, last pushed Aug 14, 2026. Figures are from public GitHub metadata via [UER-py's repository](https://github.com/dbiir/UER-py) and [awesome-pretrained-chinese-nlp-models's repository](https://github.com/lonePatient/awesome-pretrained-chinese-nlp-models). | | [UER-py](/tools/dbiir-uer-py.md) | [awesome-pretrained-chinese-nlp-models](/tools/lonepatient-awesome-pretrained-chinese-nlp-models.md) | | --- | --- | --- | | Tagline | Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo | Curated list of high-quality Chinese pretrained NLP models | | Stars | 3,112 | 5,579 | | Forks | 520 | 514 | | Open issues | 136 | 6 | | Language | Python | Python | | Adopt for | UER-py, an open-source PyTorch framework with a diverse model zoo for training and fine-tuning language models. | A comprehensive collection of advanced Chinese NLP models including large language models and multimodal setups. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | MIT | | Categories | LLM Frameworks, Model Training | LLM Frameworks, Model Training | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [UER-py](/tools/dbiir-uer-py.md) | [awesome-pretrained-chinese-nlp-models](/tools/lonepatient-awesome-pretrained-chinese-nlp-models.md) | | --- | --- | --- | | Maintenance | Dormant (18%) | Very active (96%) | | Days since push | 836d | 3d | | Open issues (now) | 136 | 6 | | Stars delta | +2 (30d) | +8 (30d) | | Owner type | Organization | User | | Full report | [trust report](/tools/dbiir-uer-py/trust.md) | [trust report](/tools/lonepatient-awesome-pretrained-chinese-nlp-models/trust.md) | ## Decision facts: UER-py - **Pricing:** freemium - The framework itself is free and open-source under Apache 2.0 license providing flexibility for modification with no costs. - **Requirements:** Min 8 GB RAM; - Requires Python environment setup; - Needs PyTorch installation - **Adopt for:** UER-py, an open-source PyTorch framework with a diverse model zoo for training and fine-tuning language models. ## Decision facts: awesome-pretrained-chinese-nlp-models - **Adopt for:** A comprehensive collection of advanced Chinese NLP models including large language models and multimodal setups. ## Choose when ### Choose UER-py if… - License: UER-py is Apache-2.0, awesome-pretrained-chinese-nlp-models is MIT. - Pricing: The framework itself is free and open-source under Apache 2.0 license providing flexibility for modification with no costs.. - Requirements: Min 8 GB RAM; - Requires Python environment setup; - Needs PyTorch installation. - Tags unique to UER-py: albert, bart, classification, clue. - - When you need to work exclusively within the PyTorch ecosystem, UER-py provides extensive support for various pre-trained models and tasks without the necessity of switching frameworks. ### Choose awesome-pretrained-chinese-nlp-models if… - License: awesome-pretrained-chinese-nlp-models is MIT, UER-py is Apache-2.0. - Tags unique to awesome-pretrained-chinese-nlp-models: dataset, ernie, gpt, large language models. - When developing applications requiring high-quality, Chinese-specific large language model support ## When NOT to use UER-py - - When you require more framework flexibility and are open to using TensorFlow or other deep learning libraries outside PyTorch. - - If your project is sensitive to maintenance updates but the UER-py repository has not seen recent active contribution, preferring a tool actively maintained might be better. ## When NOT to use awesome-pretrained-chinese-nlp-models - If the application requires extensive Western-language model integration - Projects needing non-Chinese-specific fine-tuning or training will find limited utility ## Common questions ### What is the difference between UER-py and awesome-pretrained-chinese-nlp-models? UER-py: Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo. awesome-pretrained-chinese-nlp-models: Curated list of high-quality Chinese pretrained NLP models. See the comparison table for live GitHub stats and shared categories. ### When should I choose UER-py over awesome-pretrained-chinese-nlp-models? Choose UER-py over awesome-pretrained-chinese-nlp-models when License: UER-py is Apache-2.0, awesome-pretrained-chinese-nlp-models is MIT; Pricing: The framework itself is free and open-source under Apache 2.0 license providing flexibility for modification with no costs.; Requirements: Min 8 GB RAM; - Requires Python environment setup; - Needs PyTorch installation; Tags unique to UER-py: albert, bart, classification, clue; - When you need to work exclusively within the PyTorch ecosystem, UER-py provides extensive support for various pre-trained models and tasks without the necessity of switching frameworks. ### When should I choose awesome-pretrained-chinese-nlp-models over UER-py? Choose awesome-pretrained-chinese-nlp-models over UER-py when License: awesome-pretrained-chinese-nlp-models is MIT, UER-py is Apache-2.0; Tags unique to awesome-pretrained-chinese-nlp-models: dataset, ernie, gpt, large language models; When developing applications requiring high-quality, Chinese-specific large language model support. ### When should I avoid UER-py? - When you require more framework flexibility and are open to using TensorFlow or other deep learning libraries outside PyTorch. - If your project is sensitive to maintenance updates but the UER-py repository has not seen recent active contribution, preferring a tool actively maintained might be better. ### When should I avoid awesome-pretrained-chinese-nlp-models? If the application requires extensive Western-language model integration Projects needing non-Chinese-specific fine-tuning or training will find limited utility ### Is UER-py or awesome-pretrained-chinese-nlp-models more popular on GitHub? awesome-pretrained-chinese-nlp-models has more GitHub stars (5,579 vs 3,112). Stars measure visibility, not whether either tool fits your constraints. ### Are UER-py and awesome-pretrained-chinese-nlp-models open source? Yes - both are open-source projects on GitHub (UER-py: Apache-2.0, awesome-pretrained-chinese-nlp-models: MIT). ### Where can I find alternatives to UER-py or awesome-pretrained-chinese-nlp-models? GraphCanon lists graph-backed alternatives at [UER-py alternatives](/tools/dbiir-uer-py/alternatives) and [awesome-pretrained-chinese-nlp-models alternatives](/tools/lonepatient-awesome-pretrained-chinese-nlp-models/alternatives) ([UER-py markdown twin](/tools/dbiir-uer-py/alternatives.md), [awesome-pretrained-chinese-nlp-models markdown twin](/tools/lonepatient-awesome-pretrained-chinese-nlp-models/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/dbiir-uer-py-vs-lonepatient-awesome-pretrained-chinese-nlp-models.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, UER-py or awesome-pretrained-chinese-nlp-models? UER-py: Dormant. awesome-pretrained-chinese-nlp-models: Very active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for UER-py and awesome-pretrained-chinese-nlp-models? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [UER-py trust report](/tools/dbiir-uer-py/trust); [awesome-pretrained-chinese-nlp-models trust report](/tools/lonepatient-awesome-pretrained-chinese-nlp-models/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=dbiir-uer-py`](/api/graphcanon/graph?tool=dbiir-uer-py) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_