Instructions to use SynLayers/Bbox-caption-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SynLayers/Bbox-caption-8b with Transformers:

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

pipe = pipeline("image-text-to-text", model="SynLayers/Bbox-caption-8b")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("SynLayers/Bbox-caption-8b")
model = AutoModelForImageTextToText.from_pretrained("SynLayers/Bbox-caption-8b")
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

vLLM

How to use SynLayers/Bbox-caption-8b with vLLM:

Install from pip and serve model

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

SGLang

How to use SynLayers/Bbox-caption-8b 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 "SynLayers/Bbox-caption-8b" \
    --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": "SynLayers/Bbox-caption-8b",
		"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 "SynLayers/Bbox-caption-8b" \
        --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": "SynLayers/Bbox-caption-8b",
		"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 SynLayers/Bbox-caption-8b with Docker Model Runner:
```
docker model run hf.co/SynLayers/Bbox-caption-8b
```

SynLayers commited on 7 days ago

Commit

0dd3d3d

verified ·

1 Parent(s): 82299c8

Upload demo/README.md with huggingface_hub

Browse files

Files changed (1) hide show

demo/README.md +1 -102

demo/README.md CHANGED Viewed

@@ -6,7 +6,7 @@ colorTo: purple
 sdk: gradio
 python_version: "3.10"
 app_file: app.py
-suggested_hardware: H800
 models:
   - SynLayers/Bbox-caption-8b
 pinned: false
@@ -20,7 +20,6 @@ This folder now contains a unified real-world inference demo:
 2. `infer/infer.py` runs SynLayers decomposition with `infer/infer.yaml`.
 3. `demo/real_world_pipeline.py` stitches the two stages together for one uploaded image.
 4. `demo/app.py` provides a Gradio interface that can be used locally or adapted for a Hugging Face Space.
-5. `demo/upload_used_bundle_to_hf.py` uploads only the Python/config files actually used by the demo, plus the selected runtime assets.
 ## Local Run
@@ -37,104 +36,4 @@ python demo/real_world_pipeline.py \
   --image "/path/to/your/image.png"
 ```
-## Default Models
-The current local defaults are:
-- bbox-caption model:
-  `/project/llmsvgen/share/data/kmw_layered_checkpoint/Bbox-caption-8b`
-- SynLayers base checkpoints:
-  `/project/llmsvgen/share/data/kmw_layered_checkpoint/SynLayers_checkpoints`
-- SynLayers decomposition checkpoint:
-  `/project/llmsvgen/share/data/kmw_layered_checkpoint/SynLayers_ckpt/step_120000`
-- base config:
-  `infer/infer.yaml`
-## Hugging Face Space Notes
-The Gradio app is ready for a Hugging Face Space.
-After you upload the model/runtime bundle to `SynLayers/Bbox-caption-8b`, the Space can download
-those uploaded assets automatically and use them directly.
-The app supports overriding the local defaults with environment variables:
-- `SYNLAYERS_MODEL_REPO`
-- `SYNLAYERS_BBOX_MODEL`
-- `SYNLAYERS_BASE_MODEL`
-- `SYNLAYERS_ADAPTER_MODEL`
-- `SYNLAYERS_TRANSP_VAE`
-- `SYNLAYERS_PRETRAINED_LORA`
-- `SYNLAYERS_ARTPLUS_LORA`
-- `SYNLAYERS_DECOMP_CKPT_ROOT`
-- `SYNLAYERS_REAL_CONFIG`
-- `SYNLAYERS_DEMO_WORK_DIR`
-- `SYNLAYERS_EXAMPLE_DIR`
-In practice, for a real Hugging Face Space deployment you will want to:
-1. upload the required model/runtime assets to `SynLayers/Bbox-caption-8b`
-2. create a Gradio Space repo, for example `SynLayers/synlayers-real-world-demo`
-3. upload the Space scaffold with `demo/publish_space.py`
-4. set `SYNLAYERS_MODEL_REPO=SynLayers/Bbox-caption-8b` in the Space settings
-5. launch `app.py` as the Space entrypoint
-### Public interface flow
-1. Upload the model/runtime bundle:
-```bash
-python demo/upload_used_bundle_to_hf.py \
-  --repo-id SynLayers/Bbox-caption-8b
-```
-2. Create and upload the Space scaffold:
-```bash
-python demo/publish_space.py \
-  --repo-id SynLayers/synlayers-real-world-demo
-```
-3. In the Hugging Face Space settings, add:
-```text
-SYNLAYERS_MODEL_REPO=SynLayers/Bbox-caption-8b
-```
-Then the public Space interface will:
-- accept a user image upload
-- load the bbox-caption model from the uploaded model repo
-- download the SynLayers decomposition assets from that same repo
-- run the one-step decomposition pipeline
-- return the bbox visualization, merged output, per-layer outputs, and a downloadable archive
-## Upload Bundle
-To upload the minimal used demo bundle to a Hugging Face repo:
-```bash
-python demo/upload_used_bundle_to_hf.py \
-  --repo-id SynLayers/Bbox-caption-8b
-```
-This uploads:
-- the used `demo`, `infer`, `models`, and `tools` Python files
-- `demo/upload_used_bundle_to_hf.py`
-- `demo/publish_space.py`
-- `infer/infer.yaml`
-- `environment.yml`
-- `ckpt/trans_vae/0008000.pt`
-- `ckpt/pre_trained_LoRA/pytorch_lora_weights.safetensors`
-- `ckpt/prism_ft_LoRA/pytorch_lora_weights.safetensors`
-- `SynLayers_ckpt/step_120000`
-- `SynLayers_checkpoints/FLUX.1-dev`
-- `SynLayers_checkpoints/FLUX.1-dev-Controlnet-Inpainting-Alpha`
-## Fixed Prompt
-The bbox detector always uses the fixed prompt defined in:
-- `demo/infer/run_caption_bbox_infer.py`
-No extra user text prompt is required.

 sdk: gradio
 python_version: "3.10"
 app_file: app.py
+suggested_hardware: a100-large
 models:
   - SynLayers/Bbox-caption-8b
 pinned: false
 2. `infer/infer.py` runs SynLayers decomposition with `infer/infer.yaml`.
 3. `demo/real_world_pipeline.py` stitches the two stages together for one uploaded image.
 4. `demo/app.py` provides a Gradio interface that can be used locally or adapted for a Hugging Face Space.
 ## Local Run
   --image "/path/to/your/image.png"
 ```