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
```

nielsr HF Staff commited on Jul 2, 2025

Commit

09ae5dd

verified ·

1 Parent(s): c59d17c

Add pipeline tag

Browse files

This PR adds the `pipeline_tag: text-generation` to the model card's metadata. This ensures that the model can be properly categorized and discovered on the Hugging Face Hub, appearing under searches for text generation models.

Files changed (1) hide show

README.md +8 -3

README.md CHANGED Viewed

@@ -1,6 +1,5 @@
 ---
 base_model: google/gemma-2-9b
-license: cc-by-nc-sa-4.0
 language:
 - de
 - nl
@@ -25,6 +24,8 @@ language:
 - ro
 - fi
 library_name: transformers
 ---
 ![Tower Plus Pareto](./Tower-plus-pareto.png)
@@ -71,7 +72,9 @@ sampling_params = SamplingParams(
   max_tokens=8192,
 )
 llm = LLM(model="Unbabel/Tower-Plus-9B", tensor_parallel_size=1)
-messages = [{"role": "user", "content": "Translate the following English source text to Portuguese (Portugal):\nEnglish: Hello world!\nPortuguese (Portugal): "}]
 outputs = llm.chat(messages, sampling_params)
 # Make sure your prompt_token_ids look like this
 print (outputs[0].outputs[0].text)
@@ -89,7 +92,9 @@ from transformers import pipeline
 pipe = pipeline("text-generation", model="Unbabel/Tower-Plus-9B", device_map="auto")
 # We use the tokenizer’s chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
-messages = [{"role": "user", "content": "Translate the following English source text to Portuguese (Portugal):\nEnglish: Hello world!\nPortuguese (Portugal): "}]
 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"])

 ---
 base_model: google/gemma-2-9b
 language:
 - de
 - nl
 - ro
 - fi
 library_name: transformers
+license: cc-by-nc-sa-4.0
+pipeline_tag: text-generation
 ---
 ![Tower Plus Pareto](./Tower-plus-pareto.png)
   max_tokens=8192,
 )
 llm = LLM(model="Unbabel/Tower-Plus-9B", tensor_parallel_size=1)
+messages = [{"role": "user", "content": "Translate the following English source text to Portuguese (Portugal):
+English: Hello world!
+Portuguese (Portugal): "}]
 outputs = llm.chat(messages, sampling_params)
 # Make sure your prompt_token_ids look like this
 print (outputs[0].outputs[0].text)
 pipe = pipeline("text-generation", model="Unbabel/Tower-Plus-9B", device_map="auto")
 # We use the tokenizer’s chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
+messages = [{"role": "user", "content": "Translate the following English source text to Portuguese (Portugal):
+English: Hello world!
+Portuguese (Portugal): "}]
 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"])