Instructions to use mobileforge-anonymous/ForgeQwen3-8B-200tasks with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mobileforge-anonymous/ForgeQwen3-8B-200tasks with Transformers:

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

pipe = pipeline("image-text-to-text", model="mobileforge-anonymous/ForgeQwen3-8B-200tasks")
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("mobileforge-anonymous/ForgeQwen3-8B-200tasks")
model = AutoModelForMultimodalLM.from_pretrained("mobileforge-anonymous/ForgeQwen3-8B-200tasks", 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 mobileforge-anonymous/ForgeQwen3-8B-200tasks with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mobileforge-anonymous/ForgeQwen3-8B-200tasks"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mobileforge-anonymous/ForgeQwen3-8B-200tasks",
		"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/mobileforge-anonymous/ForgeQwen3-8B-200tasks

SGLang

How to use mobileforge-anonymous/ForgeQwen3-8B-200tasks 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 "mobileforge-anonymous/ForgeQwen3-8B-200tasks" \
    --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": "mobileforge-anonymous/ForgeQwen3-8B-200tasks",
		"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 "mobileforge-anonymous/ForgeQwen3-8B-200tasks" \
        --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": "mobileforge-anonymous/ForgeQwen3-8B-200tasks",
		"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 mobileforge-anonymous/ForgeQwen3-8B-200tasks with Docker Model Runner:
```
docker model run hf.co/mobileforge-anonymous/ForgeQwen3-8B-200tasks
```

ForgeQwen3-8B-200tasks

ForgeQwen3-8B-200tasks is the Qwen3-VL-8B-Instruct policy adapted with MobileForge on 200 automatically generated target-app tasks. MobileForge uses the policy's own rollouts, hierarchical critic feedback, corrective hints, and hint-contextualized step-level GRPO. No human-written adaptation tasks, demonstrations, or reward labels are used.

This repository is part of an anonymous ICLR submission artifact. Author and paper-identifying metadata will be added after review.

Anonymous project page: https://mobileforge-anonymous.github.io/

Evaluation

On AndroidWorld (116 tasks), this checkpoint obtains 55/116 (47.4%) Pass@1, 64/116 (55.2%) Pass@2, and 71/116 (61.2%) Pass@3.

Reproduction code and raw evaluation archives are available from the anonymous code repository and benchmark-results dataset.

Usage and limitations

Use the loading and prompting interface of Qwen/Qwen3-VL-8B-Instruct. The model can make incorrect or unsafe GUI actions; run it only in isolated test environments and inspect actions before using it with personal data.

Downloads last month: -

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for mobileforge-anonymous/ForgeQwen3-8B-200tasks

Base model

Qwen/Qwen3-VL-8B-Instruct

Finetuned

(551)

this model

Collection including mobileforge-anonymous/ForgeQwen3-8B-200tasks

MobileForge-Models

Collection

Model checkpoints for the anonymous MobileForge submission artifact. • 6 items • Updated about 4 hours ago