Instructions to use davidan03/qwen3.5-0.8b-openwebrl-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use davidan03/qwen3.5-0.8b-openwebrl-sft with Transformers:

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

pipe = pipeline("image-text-to-text", model="davidan03/qwen3.5-0.8b-openwebrl-sft")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("davidan03/qwen3.5-0.8b-openwebrl-sft")
model = AutoModelForMultimodalLM.from_pretrained("davidan03/qwen3.5-0.8b-openwebrl-sft", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use davidan03/qwen3.5-0.8b-openwebrl-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "davidan03/qwen3.5-0.8b-openwebrl-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "davidan03/qwen3.5-0.8b-openwebrl-sft",
		"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/davidan03/qwen3.5-0.8b-openwebrl-sft

SGLang

How to use davidan03/qwen3.5-0.8b-openwebrl-sft 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 "davidan03/qwen3.5-0.8b-openwebrl-sft" \
    --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": "davidan03/qwen3.5-0.8b-openwebrl-sft",
		"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 "davidan03/qwen3.5-0.8b-openwebrl-sft" \
        --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": "davidan03/qwen3.5-0.8b-openwebrl-sft",
		"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 davidan03/qwen3.5-0.8b-openwebrl-sft with Docker Model Runner:
```
docker model run hf.co/davidan03/qwen3.5-0.8b-openwebrl-sft
```

qwen3.5-0.8b-openwebrl-sft

Qwen/Qwen3.5-0.8B fully fine-tuned on the OpenWebRL SFT trajectories (multi-turn web-browsing episodes with screenshots), using the same recipe as the released OpenWebRL-4B-SFT model.

Usage notes

Serve with chat_template_kwargs={"enable_thinking": True}. The Qwen3.5-0.8B chat template turns thinking OFF by default, but every training target begins with a <think> block. The base model's multi-token-prediction (mtp.*) weights are not included, so MTP speculative decoding is unavailable; ordinary serving is unaffected.

Training

Data: OpenWebRL SFT trajectories, 3,084 per-turn rows, rendered with LlamaFactory's qwen3_5 template (history masked; only the final assistant turn of each row is trained).
Full fine-tune with LlamaFactory: vision tower frozen (88,004,352 params); projector and language model trained (764,981,568 of 852,985,920 params).
3 epochs (75 optimizer steps), learning rate 1e-5, cosine schedule, warmup 0.1, effective batch 128 (1 per device x 64 accumulation x 2 GPUs), bf16, DeepSpeed ZeRO-2, cutoff 36,864 tokens, image_max_pixels 12,845,056.
2 x H200, about 45 minutes.
Mean training loss by epoch: 0.829 / 0.591 / 0.479. No held-out split was used; most of the drop after epoch 1 comes at epoch boundaries (repeat passes over the data).

Evaluation

Not yet evaluated.

Downloads last month: 48

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for davidan03/qwen3.5-0.8b-openwebrl-sft

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Finetuned

(783)

this model