Instructions to use insagur/qwen3.5-9b-agentnet-ubuntu-1epoch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use insagur/qwen3.5-9b-agentnet-ubuntu-1epoch with Transformers:

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

pipe = pipeline("image-text-to-text", model="insagur/qwen3.5-9b-agentnet-ubuntu-1epoch")
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("insagur/qwen3.5-9b-agentnet-ubuntu-1epoch")
model = AutoModelForMultimodalLM.from_pretrained("insagur/qwen3.5-9b-agentnet-ubuntu-1epoch")
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 insagur/qwen3.5-9b-agentnet-ubuntu-1epoch with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "insagur/qwen3.5-9b-agentnet-ubuntu-1epoch"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "insagur/qwen3.5-9b-agentnet-ubuntu-1epoch",
		"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/insagur/qwen3.5-9b-agentnet-ubuntu-1epoch

SGLang

How to use insagur/qwen3.5-9b-agentnet-ubuntu-1epoch 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 "insagur/qwen3.5-9b-agentnet-ubuntu-1epoch" \
    --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": "insagur/qwen3.5-9b-agentnet-ubuntu-1epoch",
		"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 "insagur/qwen3.5-9b-agentnet-ubuntu-1epoch" \
        --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": "insagur/qwen3.5-9b-agentnet-ubuntu-1epoch",
		"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 insagur/qwen3.5-9b-agentnet-ubuntu-1epoch with Docker Model Runner:
```
docker model run hf.co/insagur/qwen3.5-9b-agentnet-ubuntu-1epoch
```

Qwen3.5-9B AgentNet Ubuntu (1 Epoch, Legacy Format)

Full fine-tuning of Qwen/Qwen3.5-9B on the AgentNet Ubuntu split (5K trajectories → 38,317 step-level samples after quality filtering).

Training format

Legacy Thought: / Action: / Code: template (no ## headers). For the OpenCUA ## format variant see insagur/qwen3.5-9b-agentnet-cot-l2-step100.

Thought: <reasoning>
Action: <one-sentence>
Code:
pyautogui.click(x=0.5, y=0.5)

Coordinates are normalized to [0, 1] of screen width/height.

Training config

Hardware: 1 × 8 A100 80GB SXM4
Distributed: DeepSpeed ZeRO-2 + bf16
Optimizer: AdamW, LR 1e-5 cosine, warmup 200 steps
Batch: per_device_bs=1 × grad_accum=16 × 8 GPU = global batch 128
Epochs: 1 (300 steps)
EMA teacher: target=block (last ViT block), decay=0.9995, α=0.5
Sequence length: 3072 (truncated; p99=2713)
Image tokens: 2048 (≈1.6M pixel cap; ~1689×950 post-resize)
Gradient checkpointing: on
Train runtime: 5h 14m

Metrics (final)

Metric	Value
Train loss	0.4726
Train token_acc	0.854
Eval loss	0.4622
Eval token_acc	0.841
Eval samples	1866

Offline eval on 50 val samples (scripts/eval.py):

Metric	Value
parses_ok_frac	0.18
coord_l2 (parsed)	0.219
click_hit_rate (parsed)	0.60
action_kind_match	0.57

Format adherence is the main limitation — the legacy bare-prefix format isn't reliably emitted by Qwen3.5; the OpenCUA ## variant addresses this.

Data

AgentNet Ubuntu 5K trajectories filtered with task_completed AND alignment≥7 AND efficiency≥5 and per-step last_step_correct AND NOT last_step_redundant. 5% trajectory-level val split.

Split	Trajectories	Samples
Train	2,178	38,317
Val	114	1,866

Inference

from transformers import AutoModelForImageTextToText, AutoProcessor
from PIL import Image

model = AutoModelForImageTextToText.from_pretrained(
    "insagur/qwen3.5-9b-agentnet-ubuntu-1epoch",
    torch_dtype="bfloat16",
).to("cuda")
processor = AutoProcessor.from_pretrained("insagur/qwen3.5-9b-agentnet-ubuntu-1epoch")

system = (
    "You are a computer-use agent operating a Linux desktop. "
    "You receive the user's task and the current screenshot. "
    "Respond with your reasoning, the action description, and the pyautogui code to execute. "
    "All coordinates are normalized to [0, 1] of screen width/height. "
    "Format your response exactly as:\n"
    "Thought: <your reasoning>\nAction: <one-sentence description of the next action>\nCode:\n<pyautogui code>"
)
image = Image.open("screenshot.png").convert("RGB")
messages = [
    {"role": "system", "content": system},
    {"role": "user", "content": [
        {"type": "image", "image": image},
        {"type": "text", "text": "Task: Open the terminal.\n<image>\nWhat is the next action?"},
    ]},
]
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[text], images=[image], return_tensors="pt").to("cuda")
out = model.generate(**inputs, max_new_tokens=256)
print(processor.batch_decode(out, skip_special_tokens=True)[0])

Recipe

Training code: https://github.com/2bhapby/gui_internal_worldmodel

SMOKE=0 WANDB=1 DS=z2 NPROC=8 PER_DEVICE_BS=1 GRAD_ACCUM=16 \
RUN_NAME=a100-full-9b-1epoch \
sbatch --gpus=8 scripts/slurm_train_qwen35_4b_agentnet.sbatch \
  optim.num_train_epochs=1

Downloads last month: 19

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for insagur/qwen3.5-9b-agentnet-ubuntu-1epoch

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(373)

this model

insagur
/

qwen3.5-9b-agentnet-ubuntu-1epoch