| --- |
| license: apache-2.0 |
| base_model: Helsinki-NLP/opus-mt-lt-eo |
| library_name: transformers |
| pipeline_tag: translation |
| tags: |
| - translation |
| - marian |
| --- |
| |
| # translate-lt-eo |
|
|
| > Part of the Windstorm Labs open model catalogue. Scores, licence and attribution for every model: https://windytranslate.com/models/translate-lt-eo |
|
|
| Machine translation model, `lt` to `eo`, published by Windstorm Labs. |
|
|
| ## Attribution |
|
|
| Derived from [`Helsinki-NLP/opus-mt-lt-eo`](https://huggingface.co/Helsinki-NLP/opus-mt-lt-eo), licensed **apache-2.0**. |
| Windstorm Labs did not train the original model. This notice provides the attribution the |
| licence requires. |
|
|
| ## What was changed |
|
|
| **The weights in this repository have been modified from the original.** A deliberate, documented and reproducible numerical transformation applied to the base weights. It is not a training run and is not described as one. |
|
|
| | | | |
| |---|---| |
| | Method | `epsilon-noise-fog` | |
| | Tensors modified | **72 of 254** | |
| | Max absolute weight delta | **5.234e-07** | |
| | Verified | tensor-by-tensor against the upstream original, 2026-07-26 | |
|
|
| The comparison is tensor-level rather than file-level: safetensors and PyTorch `.bin` |
| containers hash differently even when the tensors inside are identical, so a file-hash |
| mismatch would prove nothing. |
|
|
| ## Contents |
|
|
| A single transformers build in safetensors format, loadable directly: |
|
|
| ```python |
| from transformers import AutoTokenizer, AutoModelForSeq2SeqLM |
| |
| tok = AutoTokenizer.from_pretrained("WindyTranslate/translate-lt-eo") |
| model = AutoModelForSeq2SeqLM.from_pretrained("WindyTranslate/translate-lt-eo") |
| |
| batch = tok(["<your text here>"], return_tensors="pt", padding=True) |
| print(tok.batch_decode(model.generate(**batch), skip_special_tokens=True)) |
| ``` |
|
|
| Other builds of this pair, including CTranslate2 INT8, are not included in this repository. |
|
|
| ## Evaluation |
|
|
| | Benchmark | chrF++ | BLEU | Band | |
| |---|---:|---:|---| |
| | FLORES-200 dev, 48 sentences (Lithuanian → Esperanto) | 19.70 | 2.61 | Limited | |
|
|
| Measured 2026-08-04; screening score, not a publication result. Bands: Excellent ≥60, Good 45–60, Usable 30–45, Limited 15–30, Not recommended <15 (chrF++). |
|
|
| ## Limitations |
|
|
| - A single language direction: `lt` to `eo`. |
| - The evaluation above is a 48-sentence screening score, not a publication result. The weights are |
| verified to differ from the original; that is a statement about provenance. |
| - Quality is not monotonic with model size or with the amount of fine-tuning applied. |
|
|
