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

Libraries

How to use Ryex/Tower-Plus-9B-abliterated-hf-data with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ryex/Tower-Plus-9B-abliterated-hf-data")
model = AutoModelForCausalLM.from_pretrained("Ryex/Tower-Plus-9B-abliterated-hf-data")
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 Settings

vLLM

How to use Ryex/Tower-Plus-9B-abliterated-hf-data with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Ryex/Tower-Plus-9B-abliterated-hf-data

SGLang

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

Docker Model Runner
How to use Ryex/Tower-Plus-9B-abliterated-hf-data with Docker Model Runner:
```
docker model run hf.co/Ryex/Tower-Plus-9B-abliterated-hf-data
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model ID

A fairly effective attempt at uncensoring Tower Plus, while maintaining some core functionality. Below is taken directly from Unbabel/Tower-Plus-9B

Usage:

When using the model, make sure your prompt is formated correctly!

Also, we recommend using VLLM rather than Hugging Face.

Using on VLLM:

# pip install vllm
# Gemma by default only uses 4k context. You need to set the following variables:
# export VLLM_WORKER_MULTIPROC_METHOD=spawn
# export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1

from vllm import LLM, SamplingParams

sampling_params = SamplingParams(
  best_of=1,
  temperature=0,
  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)
# > Olá, mundo!

Using on Transformers:

# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate
import torch
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"])

Citation

@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}, 
}