Instructions to use namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep with Transformers:

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

pipe = pipeline("image-text-to-text", model="namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep")
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("namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep")
model = AutoModelForMultimodalLM.from_pretrained("namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep", 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 namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep",
		"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/namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep

SGLang

How to use namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep 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 "namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep" \
    --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": "namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep",
		"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 "namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep" \
        --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": "namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep",
		"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 namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep with Docker Model Runner:
```
docker model run hf.co/namhokaist/appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep
```

appgen-qwen3-vl-8b-sft-ngc-amex-avariant-E-ngc-lr2p5e7-1ep / README.md

namhokaist

Publish frozen Qwen3 NGC-v1 arm E step=113 data=8890e2fe596e

6cdf0aa verified 3 days ago

preview code

Raw

History Blame Contribute Delete

2.49 kB

metadata

base_model: Qwen/Qwen3-VL-8B-Instruct
datasets:
  - luca0621/appgen-sft-ngc-v1
  - Yuxiang007/AMEX
license: apache-2.0
library_name: transformers
pipeline_tag: image-text-to-text
tags:
  - qwen3-vl
  - android
  - gui-agent
  - sft
  - appgen

AppGen Qwen3-VL frozen SFT — A-variant arm E

This is arm ngc_anchor_lr2p5e7 from a preregistered four-arm follow-up to the best NGC configuration A. The language model was fully fine-tuned while the complete Qwen3-VL visual tower, merger, and deep-stack mergers remained frozen. Publication verifies every model.visual tensor byte-for-byte against the pinned base and verifies that language-model weights changed.

Training contract

Base: Qwen/Qwen3-VL-8B-Instruct at commit 0c351dd01ed87e9c1b53cbc748cba10e6187ff3b
Sources: luca0621/appgen-sft-ngc-v1 at 769ea99dbc4ff190048ae0db37eb6310dba595e0 and Yuxiang007/AMEX at 17196b29c88dd48a7fb90ef9131bc5c7bf39f26e
Dataset variant: ngc_anchor
Dataset SHA-256: 8890e2fe596e4d78714ce4309f2a59ed9632dd5d656f758c8dc4608d46a9c6bc
Exposures: 3,588; unique semantic examples: 3,168
Direct-grounding exposures: 400
Completion-retention replay exposures: 420
Image provenance: synthetic AppGen HTML-to-PNG
Coordinates: normalized 0–1000
Prompt: proven A prompt; SHA-256 67ff8adb0e78a617f3d0edcf196d4e4cc3239967a8c30619fc5afc14484ee8c0
Optimizer: full-language AdamW, learning rate 2.5e-07, cosine schedule, 5% warmup
Batch: microbatch 4 × two GPUs × gradient accumulation 4 = global batch 32
Epochs: 1; optimizer updates: 113
Loss scale: Swift default
Frozen: visual encoder and aligner; trainable: language model and LM head

Only the final checkpoint (checkpoint-113) is published. The exact system prompt is appgen_system_prompt.txt; run_manifest.json records exact hashes, the dataset receipt, overlap audit, and weight verification. Intermediate 25-step checkpoints remain local.

Evaluation and limitations

The training/evaluation overlap gate compares EXIF-transposed decoded RGBA pixels plus image dimensions against the seven pinned AW7 test suites. It also compares normalized instruction hashes. The exact pinned receipt must report zero train/eval pixel and instruction overlaps for every data variant and suite before publication. Static grounding benchmarks are not a substitute for interactive AndroidWorld task success, and no score is claimed in this card.

This model is for Android visual-agent research, not safety-critical autonomous deployment.