Instructions to use ANke121/NAS-PO-GSPO-Qwen3-VL-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ANke121/NAS-PO-GSPO-Qwen3-VL-32B with Transformers:

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

pipe = pipeline("image-text-to-text", model="ANke121/NAS-PO-GSPO-Qwen3-VL-32B")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("ANke121/NAS-PO-GSPO-Qwen3-VL-32B")
model = AutoModelForMultimodalLM.from_pretrained("ANke121/NAS-PO-GSPO-Qwen3-VL-32B", device_map="auto")
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 Settings

vLLM

How to use ANke121/NAS-PO-GSPO-Qwen3-VL-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ANke121/NAS-PO-GSPO-Qwen3-VL-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ANke121/NAS-PO-GSPO-Qwen3-VL-32B",
		"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/ANke121/NAS-PO-GSPO-Qwen3-VL-32B

SGLang

How to use ANke121/NAS-PO-GSPO-Qwen3-VL-32B 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 "ANke121/NAS-PO-GSPO-Qwen3-VL-32B" \
    --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": "ANke121/NAS-PO-GSPO-Qwen3-VL-32B",
		"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 "ANke121/NAS-PO-GSPO-Qwen3-VL-32B" \
        --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": "ANke121/NAS-PO-GSPO-Qwen3-VL-32B",
		"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 ANke121/NAS-PO-GSPO-Qwen3-VL-32B with Docker Model Runner:
```
docker model run hf.co/ANke121/NAS-PO-GSPO-Qwen3-VL-32B
```

NAS-PO-GSPO-Qwen3-VL-32B

Qwen3-VL-32B-Instruct trained for 202 RLVR steps with GSPO and NAS-PO: Native Attention-Strategy Policy Optimization for Vision-Language Models.

The GSPO backbone uses sequence-level importance ratios with token-level correction. NAS-PO adds trajectory-level NAS-AS advantage scaling and positive-anchored AAC routing consolidation.

Training

Data: ViRL39K, 38,870 examples
Rollouts per prompt: 8
Rollout / actor global batch: 384 / 128
Maximum prompt / response: 4096 / 256 tokens
Sampling: temperature 1.0, top-p 0.99
GSPO token loss with sequence averaging and clipping 3e-4 / 4e-4
AdamW bf16: learning rate 1e-6, weight decay 0.01
NAS-AS drop quantile: 0.25
AAC target loss ratio: 0.3
Hardware topology: 16 H100-class GPUs; rollout tensor parallelism 8

The paper's main results do not separately report a score for this optimizer/scale combination. No unpublished score is claimed here.

Usage

from transformers import AutoProcessor, Qwen3VLForConditionalGeneration

repo = "ANke121/NAS-PO-GSPO-Qwen3-VL-32B"
model = Qwen3VLForConditionalGeneration.from_pretrained(repo, torch_dtype="auto", device_map="auto")
processor = AutoProcessor.from_pretrained(repo)

This is a research checkpoint. Outputs may be incorrect; verify them before consequential use. Citation metadata will be added after the paper is public.

Downloads last month: 18

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for ANke121/NAS-PO-GSPO-Qwen3-VL-32B

Base model

Qwen/Qwen3-VL-32B-Instruct

Finetuned

(62)

this model

ANke121
/

NAS-PO-GSPO-Qwen3-VL-32B

NAS-PO-GSPO-Qwen3-VL-32B

Training

Usage

Model tree for ANke121/NAS-PO-GSPO-Qwen3-VL-32B

Dataset used to train ANke121/NAS-PO-GSPO-Qwen3-VL-32B