Instructions to use DeepXR/Helion-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeepXR/Helion-V2 with Transformers:

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

pipe = pipeline("text-generation", model="DeepXR/Helion-V2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("DeepXR/Helion-V2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DeepXR/Helion-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeepXR/Helion-V2"
# 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-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DeepXR/Helion-V2

SGLang

How to use DeepXR/Helion-V2 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-V2" \
    --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-V2",
		"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-V2" \
        --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-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DeepXR/Helion-V2 with Docker Model Runner:
```
docker model run hf.co/DeepXR/Helion-V2
```

Helion-V2 / ds_config_zero3.json

Trouter-Library

Create ds_config_zero3.json

9daefda verified 9 months ago

Raw

History Blame Contribute Delete

1.48 kB

	{
	"bf16": {
	"enabled": true
	},
	"zero_optimization": {
	"stage": 3,
	"offload_optimizer": {
	"device": "cpu",
	"pin_memory": true
	},
	"offload_param": {
	"device": "cpu",
	"pin_memory": true
	},
	"overlap_comm": true,
	"contiguous_gradients": true,
	"sub_group_size": 1e9,
	"reduce_bucket_size": 5e8,
	"stage3_prefetch_bucket_size": 5e8,
	"stage3_param_persistence_threshold": 1e6,
	"stage3_max_live_parameters": 1e9,
	"stage3_max_reuse_distance": 1e9,
	"stage3_gather_16bit_weights_on_model_save": true
	},
	"gradient_accumulation_steps": 32,
	"gradient_clipping": 1.0,
	"steps_per_print": 10,
	"train_batch_size": "auto",
	"train_micro_batch_size_per_gpu": "auto",
	"wall_clock_breakdown": false,
	"communication_data_type": "bf16",
	"prescale_gradients": false,
	"sparse_gradients": false,
	"compression_training": {
	"weight_quantization": {
	"shared_parameters": {},
	"different_groups": {}
	},
	"activation_quantization": {
	"shared_parameters": {},
	"different_groups": {}
	},
	"sparse_pruning": {
	"shared_parameters": {},
	"different_groups": {}
	}
	},
	"flops_profiler": {
	"enabled": false,
	"profile_step": 1,
	"module_depth": -1,
	"top_modules": 1,
	"detailed": true,
	"output_file": null
	},
	"tensorboard": {
	"enabled": true,
	"output_path": "./logs/tensorboard",
	"job_name": "helion_v2_training"
	}
	}