Aiden1020/Sotto-EN-ZH-TW-1.7B
translation model by Aiden1020
Older snapshot: check the original source for current information.
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.
Sotto-1.7B translates English subtitles into Traditional Chinese as used in Taiwan, one subtitle at a time, using up to three preceding subtitles as context. It is the quality option for viewers with a GPU, and the teacher of Sotto-0.6B. The model uses a two-turn chat format. The user turn holds the context subtitles after CTX: (one per line, may be empty) and the current subtitle after CUR:. The model outputs only the translation of the current subtitle and stops at . Output: 收到了嗎？ Without context, leave the CTX: block empty (CTX:\n\n\nCUR:\n...). Use greedy decoding. As a server (the browser extension starts it this way): With cacheprompt, you can send the next prompt without its new subtitle while waiting for it (npredict: 0); the KV cache of the known part is kept and only the new subtitle is prefilled on arrival. This idle-time prefill lowers mean latency by 31% on a…
Read the full model card ↗ · Preview checked 2026-11-01T15:08:56.183Z
Inside the original model card — Document outline
- Sotto-EN-ZH-TW-1.7B
- Model details
- Files
- Prompt format
- Usage
- llama.cpp
- WebLLM, in the browser
- llama-cpp-python
- Evaluation
- Intended use and limitations
- Citation
- License
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
Aiden1020/Sotto-EN-ZH-TW-1.7B is a translation model repository published by Aiden1020 on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- translation
- Library
- Not reported
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-10-23T06:21:38.000Z
- Last modified
- 2026-10-23T06:37:30.000Z
Compatibility and lineage
Reported languages: en, zh
Reported base models: NiuTrans/LMT-60-1.7B-Base
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 2026-10-23T06:46:00.441Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.