Instructions to use ljvmiranda921/Polyglot-OLMo3-7B-SFT-de with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ljvmiranda921/Polyglot-OLMo3-7B-SFT-de with Transformers:

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

pipe = pipeline("text-generation", model="ljvmiranda921/Polyglot-OLMo3-7B-SFT-de")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ljvmiranda921/Polyglot-OLMo3-7B-SFT-de")
model = AutoModelForCausalLM.from_pretrained("ljvmiranda921/Polyglot-OLMo3-7B-SFT-de")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ljvmiranda921/Polyglot-OLMo3-7B-SFT-de with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ljvmiranda921/Polyglot-OLMo3-7B-SFT-de"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ljvmiranda921/Polyglot-OLMo3-7B-SFT-de",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ljvmiranda921/Polyglot-OLMo3-7B-SFT-de

SGLang

How to use ljvmiranda921/Polyglot-OLMo3-7B-SFT-de 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 "ljvmiranda921/Polyglot-OLMo3-7B-SFT-de" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ljvmiranda921/Polyglot-OLMo3-7B-SFT-de",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "ljvmiranda921/Polyglot-OLMo3-7B-SFT-de" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ljvmiranda921/Polyglot-OLMo3-7B-SFT-de",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ljvmiranda921/Polyglot-OLMo3-7B-SFT-de with Docker Model Runner:
```
docker model run hf.co/ljvmiranda921/Polyglot-OLMo3-7B-SFT-de
```

Polyglot-OLMo3-7B-SFT-de

This model is a fine-tuned version of allenai/OLMo-3-1025-7B on German synthetic data, using the best teacher-student combination identified in our paper Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation.

The training data was generated by google/gemma-3-27b-it and is available in the PolyglotTeachers-SFT-Synth dataset.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ljvmiranda921/Polyglot-OLMo3-7B-SFT-de"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

messages = [{"role": "user", "content": "Hallo, wie geht es dir?"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Acknowledgements

LJVM and AK acknowledge the support of the UKRI Frontier Grant EP/Y031350/1 (EQUATE). This work was performed using joint resources provided by the Cambridge Service for Data Driven Discovery (CSD3) EP/T022159/1 and the Isambard AI National AI Research Resource (AIRR) ST/AIRR/I-A-I/1023, and the Microsoft Research Grant. LJVM would also like to thank Songbo Hu, Chen Cecilia Liu, Millicent Ochieng, and Felermino Ali for helpful and productive discussions on the project.

Citation

@misc{miranda2026polyglotteachersevaluatinglanguage,
      title={Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation}, 
      author={Lester James V. Miranda and Ivan Vulić and Anna Korhonen},
      year={2026},
      eprint={2604.11290},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2604.11290}, 
}