netease-youdao/Confucius4-T3PO
translation model by netease-youdao
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
[](./README-zh.md) [](https://github.com/netease-youdao/Confucius4-T3PO/blob/main/LICENSE) [](https://t3po.youdao.com) [](https://github.com/netease-youdao/Confucius4-T3PO) [](https://huggingface.co/netease-youdao/Confucius4-T3PO) [](https://modelscope.cn/models/netease-youdao/Confucius4-T3PO) Confucius4-T3PO (simulTaneous Translation via pareTo Policy Optimization) is a 14-billion-parameter text-to-text simultaneous machine translation (SiMT) model developed by the NetEase Youdao AI team. Its development follows a three-stage pipeline: high-quality segment-aligned data construction, streaming cold-start of the translation model, and Pareto-aware reinforcement learning for joint quality–latency optimization. It supports streaming text input and real-time READ/WRITE decisions. After receiving each fine-grained text chunk, the model dynamically decides whether to wait for further context or to immediately produce an incremental translation. Meanwhile, the model organizes the input sequence under an interleaved history protocol, enabling KV-cache reuse and reducing redundant computation overhead. This model is a T2T (text-to-text) simultaneous translation model and does not natively support speech input. To translate speech, it can be cascaded with an external streaming automatic speech recognition (ASR) model, giving an S2T (speech-to-text) pipeline. We have also…
Read the full model card ↗ · Preview checked 2026-09-26T09:34:47.900Z
Inside the original model card — Document outline
- Model Features
- Table of Contents
- 1 Evaluation Results
- 2 Model Downloads
- 3 Streaming Protocol
- 4 Quickstart
- 4.1 Python Package Usage
- 4.2 Serving with vLLM
- 5 Intended Use and Limitations
- 6 Contact
- 6.1 WeChat Group
- 6.2 Business contact
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
netease-youdao/Confucius4-T3PO is a translation model repository published by netease-youdao on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- translation
- Library
- transformers
- Recent downloads (30 days)
- 1,028
- Cumulative likes
- 65
- Hugging Face trending score
- 60
- Reported safetensors parameters
- 14,770,033,664
- Architecture
- Qwen2ForCausalLM
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-07T10:35:28.000Z
- Last modified
- 2026-09-21T09:09:33.000Z
Compatibility and lineage
Reported languages: zh, en
Reported base models: Qwen/Qwen2.5-14B
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-26T06:37:43.835Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.