ynklab/Tower-7B-d2d

Tower-7B-d2d

This model is released as part of our paper Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking. The code and paper-specific inference scripts are available in the Doc2FRC GitHub repository.

Tower-7B-d2d is a full-parameter fine-tuned version of Unbabel/TowerInstruct-Mistral-7B-v0.2 for multilingual document-level machine translation. It was fine-tuned on sardinelab/DocBlocks.

This model is trained directly on the document-to-document (d2d) translation task.

Supported translation directions

The model supports translation between English and the following languages in both directions:

• —German
• —Spanish
• —French
• —Italian
• —Korean
• —Dutch
• —Portuguese
• —Russian
• —Chinese

General usage

The example below demonstrates general model usage. For the exact inference scripts, prompting setup, and evaluation procedure used in the paper, please refer to the Doc2FRC GitHub repository.

Recommended prompt format

The model was fine-tuned with the following raw ChatML-style translation prompt:

<|im_start|>user
Translate the following source text from {SOURCE_LANGUAGE} into {TARGET_LANGUAGE}.
{SOURCE_LANGUAGE}: {SOURCE_TEXT}.
{TARGET_LANGUAGE}: <|im_end|>
<|im_start|>assistant

Use full English language names such as English, Chinese, German, or Russian.

Transformers example

Install a PyTorch build appropriate for your hardware, together with Transformers and Accelerate. PyTorch 2.6 or later is recommended for loading the current PyTorch .bin checkpoint files.

pip install "transformers>=4.56.2" accelerate

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

MODEL_ID = "ynklab/Tower-7B-d2d"

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    dtype=torch.bfloat16,
    device_map="auto",
)
model.eval()

source_language = "English"
target_language = "Chinese"
source_text = "The weather is nice today"

prompt = (
    "<|im_start|>user\n"
    f"Translate the following source text from {source_language} "
    f"into {target_language}.\n"
    f"{source_language}: {source_text}.\n"
    f"{target_language}: <|im_end|>\n"
    "<|im_start|>assistant\n"
)

# The Tower tokenizer adds the beginning-of-sequence token used during training.
inputs = tokenizer(prompt, return_tensors="pt")
inputs = {name: tensor.to(model.device) for name, tensor in inputs.items()}

with torch.inference_mode():
    outputs = model.generate(
        **inputs,
        max_new_tokens=16384,
        do_sample=False,
        repetition_penalty=1.05,
    )

generated_tokens = outputs[0, inputs["input_ids"].shape[1]:]
translation = tokenizer.decode(
    generated_tokens,
    skip_special_tokens=True,
).strip()

print(translation)

For best results, keep the combined prompt and generated translation within 32,768 tokens.

Training

• —Base model: TowerInstruct-Mistral-7B-v0.2
• —Training method: full-parameter supervised fine-tuning
• —Training data: DocBlocks document-level parallel data
• —Epochs: 2
• —Learning rate: 7e-6
• —Learning-rate scheduler: cosine
• —Warmup steps: 125
• —Maximum sequence length: 32,768 tokens
• —Training precision: bfloat16
• —Optimizer: AdamW
• —Weight decay: 0.01

License

This model preserves the CC BY-NC-SA 4.0 License distributed with its base model, TowerInstruct-Mistral-7B-v0.2. See the LICENSE file and the upstream model card for the applicable terms.

DocBlocks contains material derived from multiple sources. Users should also consult the DocBlocks dataset and the original data sources for their applicable licensing conditions.

Acknowledgements

This model is based on TowerInstruct-Mistral-7B-v0.2 and was fine-tuned using DocBlocks. Please cite our paper when using this model in academic work.

Citation

@misc{wang2026doc2frclengthconsistentdocumentlevelmachine,
      title={Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking}, 
      author={Xiaotian Wang and Youyuan Lin and Zhan Shen and Hitomi Yanaka},
      year={2026},
      eprint={2609.12674},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2609.12674}, 
}