Instructions to use DeepXR/Helion-V2.5-Rnd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeepXR/Helion-V2.5-Rnd with Transformers:

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

pipe = pipeline("text-generation", model="DeepXR/Helion-V2.5-Rnd", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DeepXR/Helion-V2.5-Rnd", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("DeepXR/Helion-V2.5-Rnd", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DeepXR/Helion-V2.5-Rnd with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeepXR/Helion-V2.5-Rnd"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepXR/Helion-V2.5-Rnd",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DeepXR/Helion-V2.5-Rnd

SGLang

How to use DeepXR/Helion-V2.5-Rnd 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-V2.5-Rnd" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepXR/Helion-V2.5-Rnd",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-V2.5-Rnd" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepXR/Helion-V2.5-Rnd",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DeepXR/Helion-V2.5-Rnd with Docker Model Runner:
```
docker model run hf.co/DeepXR/Helion-V2.5-Rnd
```

Trouter-Library commited on Dec 9, 2025

Commit

2bad6cc

verified ·

1 Parent(s): 7082d77

Update model.safetensors.index.json

Browse files

Files changed (1) hide show

model.safetensors.index.json +1 -44

model.safetensors.index.json CHANGED Viewed

@@ -12,7 +12,7 @@
     "shard_size_bytes": 1690280320,
     "shard_size_gb": 1.69,
     "shard_size_gib": 1.57,
-    "note": "Model weights distributed across 83 SafeTensors shards (shard_00 to shard_82), each 1.69GB (1.57GiB) in FP16 precision."
   },
   "weight_map": {
     "model.embed_tokens.weight": "shard_00.safetensors",
@@ -71,49 +71,6 @@
     "model.layers.31.post_attention_layernorm.weight": "shard_82.safetensors",
     "model.norm.weight": "shard_82.safetensors",
     "lm_head.weight": "shard_82.safetensors"
-  },
-  "safetensors_info": {
-    "description": "SafeTensors format provides secure, fast, and zero-copy tensor serialization",
-    "total_shards": 83,
-    "shard_naming": "shard_00.safetensors through shard_82.safetensors",
-    "parameters": "70B",
-    "precision": "float16",
-    "shard_size_gb": 1.69,
-    "shard_size_gib": 1.57,
-    "total_size_gb": 140.27,
-    "total_size_gib": 130.71,
-    "size_note": "1.69GB (decimal) = 1.57GiB (binary). File managers show GiB, imports show GB.",
-    "shard_distribution": "Each transformer layer distributed across ~2.6 shards for balanced loading",
-    "benefits": [
-      "No arbitrary code execution during loading",
-      "Lazy loading support for memory efficiency",
-      "Fast deserialization without pickle",
-      "Tensor metadata validation",
-      "Cross-platform compatibility",
-      "Memory-mapped file support",
-      "Parallel loading across multiple GPUs"
-    ],
-    "verification": "Each file includes SHA256 checksum for integrity verification",
-    "status": "released"
-  },
-  "shard_structure": {
-    "embedding_layer": {
-      "shards": ["shard_00.safetensors"],
-      "size_gb": 1.69,
-      "size_gib": 1.57
-    },
-    "transformer_layers": {
-      "layers_per_shard": "~0.39",
-      "shards_range": "shard_01.safetensors to shard_81.safetensors",
-      "size_per_shard_gb": 1.69,
-      "size_per_shard_gib": 1.57
-    },
-    "output_layer": {
-      "shards": ["shard_82.safetensors"],
-      "includes": ["model.norm.weight", "lm_head.weight"],
-      "size_gb": 1.69,
-      "size_gib": 1.57
-    }
   }
 } {
     "total_size": 140737488355328,

     "shard_size_bytes": 1690280320,
     "shard_size_gb": 1.69,
     "shard_size_gib": 1.57,
+    "note": "Model weights distributed across 83 SafeTensors shards in FP16 precision"
   },
   "weight_map": {
     "model.embed_tokens.weight": "shard_00.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "shard_82.safetensors",
     "model.norm.weight": "shard_82.safetensors",
     "lm_head.weight": "shard_82.safetensors"
   }
 } {
     "total_size": 140737488355328,