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

06be361

verified ·

1 Parent(s): 798996c

Upload dataset/dataset_construction.sh with huggingface_hub

Browse files

Files changed (1) hide show

dataset/dataset_construction.sh +82 -0

dataset/dataset_construction.sh ADDED Viewed

	@@ -0,0 +1,82 @@

+#!/usr/bin/env bash
+set -euo pipefail
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+PYTHON_BIN="${PYTHON_BIN:-python}"
+: "${BLENDED_DIR:?Set BLENDED_DIR}"
+: "${LAION_DIR:?Set LAION_DIR}"
+: "${CAPTION_DIR:?Set CAPTION_DIR}"
+: "${OUTPUT_DIR:?Set OUTPUT_DIR}"
+CAPTION_META="${CAPTION_META:-${CAPTION_DIR}/captions.jsonl}"
+NUM_SAMPLES="${NUM_SAMPLES:-500000}"
+START_INDEX="${START_INDEX:-0}"
+SEED="${SEED:-42}"
+MAX_BASE_SAMPLES="${MAX_BASE_SAMPLES:-18000}"
+MIN_DONOR_SAMPLES="${MIN_DONOR_SAMPLES:-1}"
+MAX_DONOR_SAMPLES="${MAX_DONOR_SAMPLES:-4}"
+MIN_LAYERS_PER_DONOR="${MIN_LAYERS_PER_DONOR:-0}"
+MAX_LAYERS_PER_DONOR="${MAX_LAYERS_PER_DONOR:-2}"
+MIN_LAYERS_TO_REMOVE="${MIN_LAYERS_TO_REMOVE:-1}"
+MAX_LAYERS_TO_REMOVE="${MAX_LAYERS_TO_REMOVE:-4}"
+ADDED_LAYER_MIN_SIZE="${ADDED_LAYER_MIN_SIZE:-0.9}"
+ADDED_LAYER_MAX_SIZE="${ADDED_LAYER_MAX_SIZE:-1.1}"
+LAION_PROB="${LAION_PROB:-0.60}"
+CAPTION_PROB="${CAPTION_PROB:-0.35}"
+LAION_MIN_SIZE="${LAION_MIN_SIZE:-0.3}"
+LAION_MAX_SIZE="${LAION_MAX_SIZE:-0.4}"
+CAPTION_MIN_SIZE="${CAPTION_MIN_SIZE:-0.6}"
+CAPTION_MAX_SIZE="${CAPTION_MAX_SIZE:-0.8}"
+ALPHAVAE_MIN_LAYERS="${ALPHAVAE_MIN_LAYERS:-0}"
+ALPHAVAE_MAX_LAYERS="${ALPHAVAE_MAX_LAYERS:-0}"
+ALPHAVAE_MIN_SIZE="${ALPHAVAE_MIN_SIZE:-0.25}"
+ALPHAVAE_MAX_SIZE="${ALPHAVAE_MAX_SIZE:-0.40}"
+NUM_WORKERS="${NUM_WORKERS:-64}"
+SKIP_EXISTING="${SKIP_EXISTING:-0}"
+cmd=(
+  "$PYTHON_BIN" "$SCRIPT_DIR/scaleup_dataset.py"
+  --blended_dir "$BLENDED_DIR"
+  --laion_dir "$LAION_DIR"
+  --caption_dir "$CAPTION_DIR"
+  --caption_meta "$CAPTION_META"
+  --output_dir "$OUTPUT_DIR"
+  --num_samples "$NUM_SAMPLES"
+  --start_index "$START_INDEX"
+  --seed "$SEED"
+  --min_donor_samples "$MIN_DONOR_SAMPLES"
+  --max_donor_samples "$MAX_DONOR_SAMPLES"
+  --min_layers_per_donor "$MIN_LAYERS_PER_DONOR"
+  --max_layers_per_donor "$MAX_LAYERS_PER_DONOR"
+  --added_layer_min_size "$ADDED_LAYER_MIN_SIZE"
+  --added_layer_max_size "$ADDED_LAYER_MAX_SIZE"
+  --laion_prob "$LAION_PROB"
+  --caption_prob "$CAPTION_PROB"
+  --laion_min_size "$LAION_MIN_SIZE"
+  --laion_max_size "$LAION_MAX_SIZE"
+  --caption_min_size "$CAPTION_MIN_SIZE"
+  --caption_max_size "$CAPTION_MAX_SIZE"
+  --min_layers_to_remove "$MIN_LAYERS_TO_REMOVE"
+  --max_layers_to_remove "$MAX_LAYERS_TO_REMOVE"
+  --alphavae_min_layers "$ALPHAVAE_MIN_LAYERS"
+  --alphavae_max_layers "$ALPHAVAE_MAX_LAYERS"
+  --alphavae_min_size "$ALPHAVAE_MIN_SIZE"
+  --alphavae_max_size "$ALPHAVAE_MAX_SIZE"
+  --max_base_samples "$MAX_BASE_SAMPLES"
+  --num_workers "$NUM_WORKERS"
+)
+if [[ -n "${ALPHAVAE_DIR:-}" ]]; then
+  cmd+=(--alphavae_dir "$ALPHAVAE_DIR")
+fi
+if [[ -n "${ALPHAVAE_PROMPTS:-}" ]]; then
+  cmd+=(--alphavae_prompts "$ALPHAVAE_PROMPTS")
+fi
+if [[ "$SKIP_EXISTING" == "1" ]]; then
+  cmd+=(--skip_existing)
+fi
+"${cmd[@]}"