Instructions to use DeepXR/Helion-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeepXR/Helion-V1 with Transformers:

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

pipe = pipeline("text-generation", model="DeepXR/Helion-V1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DeepXR/Helion-V1")
model = AutoModelForCausalLM.from_pretrained("DeepXR/Helion-V1")
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 DeepXR/Helion-V1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeepXR/Helion-V1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepXR/Helion-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DeepXR/Helion-V1

SGLang

How to use DeepXR/Helion-V1 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 "DeepXR/Helion-V1" \
    --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": "DeepXR/Helion-V1",
		"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 "DeepXR/Helion-V1" \
        --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": "DeepXR/Helion-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DeepXR/Helion-V1 with Docker Model Runner:
```
docker model run hf.co/DeepXR/Helion-V1
```

Helion-V1

Helion-V1 is a conversational AI model designed to be helpful, harmless, and honest. The model focuses on providing assistance to users in a friendly and safe manner, with built-in safeguards to prevent harmful outputs.

Model Description

Developed by: DeepXR
Model type: Causal Language Model
Language(s): English
License: Apache 2.0
Finetuned from: [Troviku-1.1]

Intended Use

Helion-V1 is designed for:

General conversational assistance
Question answering
Creative writing support
Educational purposes
Coding assistance

Direct Use

The model can be used directly for chat-based applications where safety and helpfulness are priorities.

Out-of-Scope Use

This model should NOT be used for:

Generating harmful, illegal, or unethical content
Medical, legal, or financial advice without proper disclaimers
Impersonating individuals or organizations
Creating misleading or false information

Safeguards

Helion-V1 includes safety mechanisms to:

Refuse harmful requests
Avoid generating dangerous content
Maintain respectful and helpful interactions
Protect user privacy and safety

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "DeepXR/Helion-V1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

messages = [
    {"role": "user", "content": "Hello! Can you help me with a question?"}
]

input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt")
output = model.generate(input_ids, max_length=512)
response = tokenizer.decode(output[0], skip_special_tokens=True)
print(response)

Training Details

Training Data

[Information about training data]

Training Procedure

[Information about training procedure, hyperparameters, etc.]

Evaluation

Testing Data & Metrics

[Information about evaluation metrics and results]

Limitations

The model may occasionally generate incorrect information
Performance may vary across different domains
Context window is limited
May reflect biases present in training data

Ethical Considerations

Helion-V1 has been developed with safety as a priority. However, users should:

Verify critical information from reliable sources
Use appropriate content filtering for sensitive applications
Monitor outputs in production environments
Provide proper attributions when using model outputs

Citation

@misc{helion-v1,
  author = {DeepXR},
  title = {Helion-V1: A Safe and Helpful Conversational AI},
  year = {2025},
  publisher = {HuggingFace},
  url = {https://huggingface.co/DeepXR/Helion-V1}
}

Contact

For questions or issues, please open an issue on the model repository or contact the development team.

Downloads last month: 7

Collection including DeepXR/Helion-V1

Helion-V1

Collection

Helion version 1 series • 3 items • Updated Nov 7, 2025 • 2