Instructions to use ServiceNow-AI/SuperApriel-15b-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ServiceNow-AI/SuperApriel-15b-Base with Transformers:

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

pipe = pipeline("text-generation", model="ServiceNow-AI/SuperApriel-15b-Base", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("ServiceNow-AI/SuperApriel-15b-Base", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ServiceNow-AI/SuperApriel-15b-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ServiceNow-AI/SuperApriel-15b-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ServiceNow-AI/SuperApriel-15b-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ServiceNow-AI/SuperApriel-15b-Base

SGLang

How to use ServiceNow-AI/SuperApriel-15b-Base 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 "ServiceNow-AI/SuperApriel-15b-Base" \
    --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": "ServiceNow-AI/SuperApriel-15b-Base",
		"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 "ServiceNow-AI/SuperApriel-15b-Base" \
        --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": "ServiceNow-AI/SuperApriel-15b-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ServiceNow-AI/SuperApriel-15b-Base with Docker Model Runner:
```
docker model run hf.co/ServiceNow-AI/SuperApriel-15b-Base
```

denisko Claude Opus 4.6 commited on 23 days ago

Commit

7011c3d

1 Parent(s): 9ba9a9e

Add note about vLLM pure-recurrent placement limitation

Browse files

Custom placements using only GDN/KDA mixers (no FA or SWA) are not
supported due to a vLLM KV cache coordinator constraint.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -75,6 +75,8 @@ For example, to load with the all-attention placement:
 > **Note:** This model requires `trust_remote_code=True` as it uses custom architecture code for the multi-mixer supernet.
 ## Intended Use
 SuperApriel-15b-Base is designed as a **foundation checkpoint** for:

 > **Note:** This model requires `trust_remote_code=True` as it uses custom architecture code for the multi-mixer supernet.
+> **Note:** When serving with vLLM, custom placements must include at least one attention-type layer (FA or SWA). Configurations using only recurrent mixers (GDN/KDA) are not currently supported due to a vLLM KV cache coordinator limitation. All shipped Instruct presets satisfy this requirement.
 ## Intended Use
 SuperApriel-15b-Base is designed as a **foundation checkpoint** for: