Image-Text-to-Text
Transformers
Diffusers
Safetensors
qwen3_vl
vision-language-model
image-decomposition
conversational
Instructions to use SynLayers/Bbox-caption-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
Upload demo/hf_repo_assets.py with huggingface_hub
Browse files- demo/hf_repo_assets.py +63 -0
demo/hf_repo_assets.py
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from __future__ import annotations
|
| 2 |
+
|
| 3 |
+
import os
|
| 4 |
+
from functools import lru_cache
|
| 5 |
+
from pathlib import Path
|
| 6 |
+
|
| 7 |
+
from huggingface_hub import snapshot_download
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
def get_model_repo_id() -> str | None:
|
| 11 |
+
return os.environ.get("SYNLAYERS_MODEL_REPO")
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
def get_cache_dir() -> str | None:
|
| 15 |
+
return os.environ.get("SYNLAYERS_HF_CACHE")
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
@lru_cache(maxsize=4)
|
| 19 |
+
def ensure_repo_assets(repo_id: str | None = None) -> Path | None:
|
| 20 |
+
"""Download required runtime assets from the uploaded model repo when configured."""
|
| 21 |
+
resolved_repo_id = repo_id or get_model_repo_id()
|
| 22 |
+
if not resolved_repo_id:
|
| 23 |
+
return None
|
| 24 |
+
|
| 25 |
+
allow_patterns = [
|
| 26 |
+
"SynLayers_checkpoints/FLUX.1-dev/**",
|
| 27 |
+
"SynLayers_checkpoints/FLUX.1-dev-Controlnet-Inpainting-Alpha/**",
|
| 28 |
+
"SynLayers_ckpt/step_120000/**",
|
| 29 |
+
"ckpt/trans_vae/0008000.pt",
|
| 30 |
+
"ckpt/pre_trained_LoRA/**",
|
| 31 |
+
"ckpt/prism_ft_LoRA/**",
|
| 32 |
+
]
|
| 33 |
+
|
| 34 |
+
local_root = snapshot_download(
|
| 35 |
+
repo_id=resolved_repo_id,
|
| 36 |
+
repo_type="model",
|
| 37 |
+
allow_patterns=allow_patterns,
|
| 38 |
+
cache_dir=get_cache_dir(),
|
| 39 |
+
)
|
| 40 |
+
return Path(local_root)
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
def build_repo_asset_overrides(repo_id: str | None = None) -> dict[str, str]:
|
| 44 |
+
"""Return repo-local asset paths after downloading the uploaded bundle."""
|
| 45 |
+
local_root = ensure_repo_assets(repo_id)
|
| 46 |
+
if local_root is None:
|
| 47 |
+
return {}
|
| 48 |
+
|
| 49 |
+
return {
|
| 50 |
+
"repo_root": str(local_root),
|
| 51 |
+
"decomp_ckpt_root": str(local_root / "SynLayers_ckpt" / "step_120000"),
|
| 52 |
+
"pretrained_model_name_or_path": str(
|
| 53 |
+
local_root / "SynLayers_checkpoints" / "FLUX.1-dev"
|
| 54 |
+
),
|
| 55 |
+
"pretrained_adapter_path": str(
|
| 56 |
+
local_root
|
| 57 |
+
/ "SynLayers_checkpoints"
|
| 58 |
+
/ "FLUX.1-dev-Controlnet-Inpainting-Alpha"
|
| 59 |
+
),
|
| 60 |
+
"transp_vae_path": str(local_root / "ckpt" / "trans_vae" / "0008000.pt"),
|
| 61 |
+
"pretrained_lora_dir": str(local_root / "ckpt" / "pre_trained_LoRA"),
|
| 62 |
+
"artplus_lora_dir": str(local_root / "ckpt" / "prism_ft_LoRA"),
|
| 63 |
+
}
|