Instructions to use Spravil/caption-via-translation-11_2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Spravil/caption-via-translation-11_2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Spravil/caption-via-translation-11_2B", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Spravil/caption-via-translation-11_2B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Spravil/caption-via-translation-11_2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Spravil/caption-via-translation-11_2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Spravil/caption-via-translation-11_2B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Spravil/caption-via-translation-11_2B

SGLang

How to use Spravil/caption-via-translation-11_2B 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 "Spravil/caption-via-translation-11_2B" \
    --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": "Spravil/caption-via-translation-11_2B",
		"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 "Spravil/caption-via-translation-11_2B" \
        --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": "Spravil/caption-via-translation-11_2B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Spravil/caption-via-translation-11_2B with Docker Model Runner:
```
docker model run hf.co/Spravil/caption-via-translation-11_2B
```

Scaling Laws for Conditional Emergence of Multilingual Image Captioning via Generalization from Translation

11.2B Model

The 11.2B model is built upon Google's Gemma-2 as decoder, Microsoft's Florence-2-large as encoder and is trained using a synthetic dataset. As a pre-trained version, its coverage across tasks and languages is currently limited. It supports image captioning in English and German, and facilitates multimodal machine translation from English to German, French, Spanish, Russian, and Chinese.

Getting Started

import requests
from PIL import Image
import torch
from transformers import AutoModelForCausalLM, AutoConfig, AutoProcessor, AutoTokenizer


device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model = AutoModelForCausalLM.from_pretrained("Spravil/caption-via-translation-11_2B", torch_dtype=torch_dtype, trust_remote_code=True).to(device)
tokenizer = AutoTokenizer.from_pretrained(
    "google/gemma-2-2b",
    add_bos_token=True,
    add_eos_token=True,
    padding_side="right",
    truncation_side="right",
)
processor = AutoProcessor.from_pretrained("Spravil/caption-via-translation-11_2B", trust_remote_code=True, new_tokenizer=tokenizer, use_encoder_tokenizer=True)
task = "<MORE_DETAILED_CAPTION>"
lang = "de"
prompt = f"<LANG_{lang.upper()}>{task}"
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
inputs = processor(prompt, images=image, return_tensors="pt").to(device, torch_dtype)
generated_ids = model.generate(
            **inputs,
            max_new_tokens=128,
            num_beams=4,
            do_sample=False,
            use_cache=False,
        )
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
parsed_answer = processor.post_process_generation(generated_text, task=task, image_size=(image.width, image.height))
print(parsed_answer)

Bibtex

@inproceedings{spravil2026scaling,
  title={Scaling Laws for Conditional Emergence of Multilingual Image Captioning via Generalization from Translation},
  author={Spravil, Julian and Houben, Sebastian and Behnke, Sven},
  booktitle={Proceedings of the 40th AAAI Conference on Artificial Intelligence},
  year={2026}
}