Instructions to use HenryExcellent/SciDoc-Qwen3.6-27B-SFT50 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HenryExcellent/SciDoc-Qwen3.6-27B-SFT50 with Transformers:

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

pipe = pipeline("image-text-to-text", model="HenryExcellent/SciDoc-Qwen3.6-27B-SFT50")
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("HenryExcellent/SciDoc-Qwen3.6-27B-SFT50")
model = AutoModelForMultimodalLM.from_pretrained("HenryExcellent/SciDoc-Qwen3.6-27B-SFT50", 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 HenryExcellent/SciDoc-Qwen3.6-27B-SFT50 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HenryExcellent/SciDoc-Qwen3.6-27B-SFT50"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HenryExcellent/SciDoc-Qwen3.6-27B-SFT50",
		"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/HenryExcellent/SciDoc-Qwen3.6-27B-SFT50

SGLang

How to use HenryExcellent/SciDoc-Qwen3.6-27B-SFT50 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 "HenryExcellent/SciDoc-Qwen3.6-27B-SFT50" \
    --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": "HenryExcellent/SciDoc-Qwen3.6-27B-SFT50",
		"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 "HenryExcellent/SciDoc-Qwen3.6-27B-SFT50" \
        --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": "HenryExcellent/SciDoc-Qwen3.6-27B-SFT50",
		"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 HenryExcellent/SciDoc-Qwen3.6-27B-SFT50 with Docker Model Runner:
```
docker model run hf.co/HenryExcellent/SciDoc-Qwen3.6-27B-SFT50
```

SciDoc-Qwen3.6-27B-SFT50

Merged model weights accompanying SciDocBench. SFT checkpoint at optimizer step 50.

The backbone is Qwen/Qwen3.6-27B. These are complete merged weights, not a LoRA-only adapter. Use the model's tokenizer, chat template, and image processor with a compatible Transformers or vLLM installation.

During evaluation, retain the generated response losslessly and score the final answer after reasoning extraction. See the paper for the experiment-specific training mixtures, inference settings, and checkpoint selection protocol.

upload_manifest.json and SHA256SUMS identify the files in this model release. The base model's Apache-2.0 license is included. Local training logs and private runtime configuration are not part of this repository.

Downloads last month: 43

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for HenryExcellent/SciDoc-Qwen3.6-27B-SFT50

Base model

Qwen/Qwen3.6-27B

Finetuned

(424)

this model

Paper for HenryExcellent/SciDoc-Qwen3.6-27B-SFT50

SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding

Paper • 2609.05141 • Published Sep 4