Instructions to use rausch/de-t5-sci-transfer-15k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rausch/de-t5-sci-transfer-15k with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="rausch/de-t5-sci-transfer-15k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("rausch/de-t5-sci-transfer-15k")
model = AutoModelForSeq2SeqLM.from_pretrained("rausch/de-t5-sci-transfer-15k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rausch/de-t5-sci-transfer-15k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rausch/de-t5-sci-transfer-15k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rausch/de-t5-sci-transfer-15k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rausch/de-t5-sci-transfer-15k

SGLang

How to use rausch/de-t5-sci-transfer-15k with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "rausch/de-t5-sci-transfer-15k" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rausch/de-t5-sci-transfer-15k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "rausch/de-t5-sci-transfer-15k" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rausch/de-t5-sci-transfer-15k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rausch/de-t5-sci-transfer-15k with Docker Model Runner:
```
docker model run hf.co/rausch/de-t5-sci-transfer-15k
```

DE-T5-Sci-Transfer-15k

Final German scientific model: WECHSEL-initialized EN-T5-Sci → continued for 15 000 steps on German scientific data (same regimen as DE-T5-Base-15k). Checkpoint: cross_lingual_transfer/logs/train/.../step-step=015000.ckpt.

Model Details

Base: EN-T5-Sci weights, German tokenizer
Optimizer: Adafactor, lr=1e-3, inverse sqrt schedule, warmup 1.5k, grad clip 1.0
Effective batch: 48 (per-GPU 48, grad accumulation 1)
Objective: Span corruption (15 % noise, mean span 3)

Training Data

German subset of the Unpaywall-derived scientific corpus (sliding windows 512 tokens, 50 % overlap). Same cleaning pipeline as the English run.

Evaluation (Global-MMLU, zero-shot)

Metric	EN	DE
Overall accuracy	0.2738	0.2700
Humanities	0.2559	0.2536
STEM	0.2867	0.2851
Social Sciences	0.3058	0.3055
Other	0.2562	0.2443

This is the best-performing German checkpoint across both languages in the final evaluation (evaluation_results/scientific_crosslingual_transfer_eval_full_15k).

Intended Use

Zero-shot QA in German/English scientific domains, or as a strong starting point for German task-specific fine-tuning (NER, relation extraction, etc.).

Limitations

Still inherits T5-base context length/parameter budget.
Evaluated only on Global-MMLU; downstream fine-tuning recommended for specialized tasks.
Training corpus is domain-specific (scientific); may underperform on casual text.

Citation

Please cite the thesis (Nikolas Rauscher, 2025) and the WECHSEL paper (Minixhofer et al. 2022).

Downloads last month: 11

Safetensors

Model size

0.6B params

Tensor type

F32

Collection including rausch/de-t5-sci-transfer-15k

t5-sci-en2de-continued-pretraining

Collection

6 items • Updated Nov 18, 2025 • 2