Instructions to use rausch/en-t5-sci-continued-pretraining-487k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rausch/en-t5-sci-continued-pretraining-487k with Transformers:

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

pipe = pipeline("text-generation", model="rausch/en-t5-sci-continued-pretraining-487k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("rausch/en-t5-sci-continued-pretraining-487k")
model = AutoModelForMultimodalLM.from_pretrained("rausch/en-t5-sci-continued-pretraining-487k")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rausch/en-t5-sci-continued-pretraining-487k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rausch/en-t5-sci-continued-pretraining-487k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rausch/en-t5-sci-continued-pretraining-487k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rausch/en-t5-sci-continued-pretraining-487k

SGLang

How to use rausch/en-t5-sci-continued-pretraining-487k 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/en-t5-sci-continued-pretraining-487k" \
    --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/en-t5-sci-continued-pretraining-487k",
		"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/en-t5-sci-continued-pretraining-487k" \
        --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/en-t5-sci-continued-pretraining-487k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rausch/en-t5-sci-continued-pretraining-487k with Docker Model Runner:
```
docker model run hf.co/rausch/en-t5-sci-continued-pretraining-487k
```

EN-T5-Sci

Continued-pretrained T5-base on a cleaned English scientific corpus derived from Unpaywall.
Checkpoint: pretraining_logs_lr_001_OPTIMIZED_clean_restart/.../step-487500-val_ppl-3.72168.ckpt (see conversion_info.json for provenance).

Model Details

Architecture: T5-base (12L / 12L, d_model=768, 220M params)
Objective: Span corruption (15 % noise, mean span length 3)
Sequence prep: Sliding windows of 512 tokens with 50 % overlap
Optimizer: Adafactor with linear warmup (20k) → inverse sqrt decay, lr=1e-3, grad clip=1.0
Hardware: 4× NVIDIA H100 (mixed precision, gradient accumulation 2, effective batch 384)

Training Data

English scientific text (approx. 230 GB, ~11 M docs) cleaned with DataTrove and custom regex rules (see thesis Section “Automatic Data Preprocessing”). Tokenization via SentencePiece (original T5 vocab).

Evaluation (Global-MMLU, zero-shot, Global benchmark)

Metric	EN	DE
Overall accuracy	0.2687	0.2688
Humanities	0.2419	0.2414
STEM	0.2851	0.2858
Social Sciences	0.3107	0.3107
Other	0.2510	0.2514

Full plots + per-subtask CSV: evaluation_results/scientific_crosslingual_transfer_eval_full_15k/.

Intended Use

Zero-shot scientific QA, warm-start for downstream fine-tuning on English scientific NLP tasks. Use T5ForConditionalGeneration.from_pretrained("rausch/en-t5-sci-continued-pretraining-487k").