Instructions to use Unbabel/Tower-Plus-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Unbabel/Tower-Plus-9B with Transformers:

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

pipe = pipeline("text-generation", model="Unbabel/Tower-Plus-9B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Unbabel/Tower-Plus-9B")
model = AutoModelForCausalLM.from_pretrained("Unbabel/Tower-Plus-9B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Unbabel/Tower-Plus-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Unbabel/Tower-Plus-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Unbabel/Tower-Plus-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Unbabel/Tower-Plus-9B

SGLang

How to use Unbabel/Tower-Plus-9B 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 "Unbabel/Tower-Plus-9B" \
    --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": "Unbabel/Tower-Plus-9B",
		"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 "Unbabel/Tower-Plus-9B" \
        --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": "Unbabel/Tower-Plus-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Unbabel/Tower-Plus-9B with Docker Model Runner:
```
docker model run hf.co/Unbabel/Tower-Plus-9B
```

RicardoRei commited on Jun 25, 2025

Commit

c59d17c

verified ·

1 Parent(s): 3c67f5d

Update README.md

Browse files

Files changed (1) hide show

README.md +14 -0

README.md CHANGED Viewed

@@ -93,4 +93,18 @@ messages = [{"role": "user", "content": "Translate the following English source
 input_ids = pipe.tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True)
 outputs = pipe(messages, max_new_tokens=256, do_sample=False)
 print(outputs[0]["generated_text"])
 ```

 input_ids = pipe.tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True)
 outputs = pipe(messages, max_new_tokens=256, do_sample=False)
 print(outputs[0]["generated_text"])
+```
+# Citation
+If you use this model please cite our paper:
+```
+@misc{rei2025towerplus,
+      title={Tower+: Bridging Generality and Translation Specialization in Multilingual LLMs},
+      author={Ricardo Rei and Nuno M. Guerreiro and José Pombal and João Alves and Pedro Teixeirinha and Amin Farajian and André F. T. Martins},
+      year={2025},
+      eprint={2506.17080},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2506.17080},
+}
 ```