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
```

Trouter-Library commited on Nov 4, 2025

Commit

0ca963f

verified ·

1 Parent(s): f1a0ba2

Create training_args.json

Browse files

Files changed (1) hide show

training_args.json +35 -0

training_args.json ADDED Viewed

	@@ -0,0 +1,35 @@

+{
+  "output_dir": "./helion-v1-checkpoints",
+  "num_train_epochs": 3,
+  "per_device_train_batch_size": 4,
+  "per_device_eval_batch_size": 4,
+  "gradient_accumulation_steps": 8,
+  "eval_strategy": "steps",
+  "eval_steps": 500,
+  "save_strategy": "steps",
+  "save_steps": 500,
+  "save_total_limit": 3,
+  "learning_rate": 2e-5,
+  "warmup_steps": 100,
+  "logging_steps": 10,
+  "logging_dir": "./logs",
+  "fp16": false,
+  "bf16": true,
+  "optim": "adamw_torch",
+  "weight_decay": 0.01,
+  "lr_scheduler_type": "cosine",
+  "max_grad_norm": 1.0,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": {
+    "use_reentrant": false
+  },
+  "dataloader_num_workers": 4,
+  "group_by_length": true,
+  "report_to": ["tensorboard", "wandb"],
+  "load_best_model_at_end": true,
+  "metric_for_best_model": "eval_loss",
+  "greater_is_better": false,
+  "ddp_find_unused_parameters": false,
+  "max_seq_length": 4096,
+  "packing": false
+}