Instructions to use vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone with Transformers:

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

pipe = pipeline("text-generation", model="vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone

SGLang

How to use vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone 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 "vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone" \
    --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": "vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone",
		"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 "vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone" \
        --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": "vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone with Docker Model Runner:
```
docker model run hf.co/vtava/Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone
```

Qwen3.5-0.8B-CeNN-Integrated-V1-Standalone / standalone_config.json

vtava

Add files using upload-large-folder tool

b2851cb verified 17 days ago

Raw History Blame Contribute Delete

697 Bytes

	{
	"format": "tinycenn-qwen35-standalone-v2",
	"source": "vtava/Qwen3.5-0.8B-CeNN-Integrated-V1",
	"variant": "cenn_integrated",
	"expected_class": "Qwen35IntegratedAttention",
	"layers": [
	3,
	23
	],
	"core_configs": {
	"3": {
	"num_heads": 8,
	"num_kv_heads": 2,
	"head_dim": 256,
	"feature_dim": 64,
	"variant": "cenn_partition",
	"block_size": 32,
	"sink_tokens": 4,
	"compute_dtype": "float32"
	},
	"23": {
	"num_heads": 8,
	"num_kv_heads": 2,
	"head_dim": 256,
	"feature_dim": 64,
	"variant": "cenn_partition",
	"block_size": 32,
	"sink_tokens": 4,
	"compute_dtype": "float32"
	}
	}
	}