Instructions to use GestaltLabs/Qwen3.5-9B-NSC-ACE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GestaltLabs/Qwen3.5-9B-NSC-ACE with Transformers:

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

pipe = pipeline("image-text-to-text", model="GestaltLabs/Qwen3.5-9B-NSC-ACE")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("GestaltLabs/Qwen3.5-9B-NSC-ACE")
model = AutoModelForImageTextToText.from_pretrained("GestaltLabs/Qwen3.5-9B-NSC-ACE")
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?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use GestaltLabs/Qwen3.5-9B-NSC-ACE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GestaltLabs/Qwen3.5-9B-NSC-ACE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GestaltLabs/Qwen3.5-9B-NSC-ACE",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/GestaltLabs/Qwen3.5-9B-NSC-ACE

SGLang

How to use GestaltLabs/Qwen3.5-9B-NSC-ACE 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 "GestaltLabs/Qwen3.5-9B-NSC-ACE" \
    --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": "GestaltLabs/Qwen3.5-9B-NSC-ACE",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "GestaltLabs/Qwen3.5-9B-NSC-ACE" \
        --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": "GestaltLabs/Qwen3.5-9B-NSC-ACE",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use GestaltLabs/Qwen3.5-9B-NSC-ACE with Docker Model Runner:
```
docker model run hf.co/GestaltLabs/Qwen3.5-9B-NSC-ACE
```

Qwen3.5-9B-NSC-ACE-200-Merged

This is the merged full-weight release of DJLougen/Qwen3.5-9B-NSC-ACE-200, merged into Qwen/Qwen3.5-9B.

NSC-ACE improves structured agentic tool-calling behavior, especially tool-call format reliability and required argument quality.

Highlights

Metric	Base	NSC-ACE
Held-out Acta composite structural score	0.804	0.947
Held-out Acta tool-call rate	82.5%	97.5%
Held-out Acta reasoning tag rate	47.5%	97.5%
BFCL subset exact required call accuracy	67.5%	75.0%
BFCL required argument name accuracy	82.7%	91.8%
BFCL required argument value accuracy	72.5%	81.6%

Loading

import torch
from transformers import AutoModelForImageTextToText, AutoTokenizer

model_id = "DJLougen/Qwen3.5-9B-NSC-ACE-200-Merged"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

Notes

This is a merged model for easier deployment and downstream quantization. The original PEFT adapter remains available at DJLougen/Qwen3.5-9B-NSC-ACE-200.

Downloads last month: 36

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for GestaltLabs/Qwen3.5-9B-NSC-ACE

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(274)

this model

Finetunes

1 model

GestaltLabs
/

Qwen3.5-9B-NSC-ACE

Qwen3.5-9B-NSC-ACE-200-Merged

Highlights

Loading

Notes

Model tree for GestaltLabs/Qwen3.5-9B-NSC-ACE

Dataset used to train GestaltLabs/Qwen3.5-9B-NSC-ACE