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/real_world_pipeline.py with huggingface_hub
Browse files- demo/real_world_pipeline.py +15 -0
demo/real_world_pipeline.py
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
from __future__ import annotations
|
| 2 |
|
| 3 |
import argparse
|
|
|
|
| 4 |
import json
|
| 5 |
import os
|
| 6 |
import re
|
|
@@ -95,6 +96,19 @@ def load_bbox_bundle(model_path: str):
|
|
| 95 |
return model, processor
|
| 96 |
|
| 97 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
def load_real_bundle(config: dict):
|
| 99 |
key = (
|
| 100 |
config.get("pretrained_model_name_or_path"),
|
|
@@ -390,6 +404,7 @@ def run_real_world_pipeline(
|
|
| 390 |
bbox_jsonl = write_bbox_jsonl(record, run_dir / "caption_bbox_infer.jsonl")
|
| 391 |
bbox_vis_path = run_dir / "bbox_vis" / f"{normalized_sample_name}_vis.png"
|
| 392 |
draw_boxes(prepared_image_path, bboxes, bbox_vis_path)
|
|
|
|
| 393 |
|
| 394 |
config = build_runtime_config(
|
| 395 |
config_path=config_path,
|
|
|
|
| 1 |
from __future__ import annotations
|
| 2 |
|
| 3 |
import argparse
|
| 4 |
+
import gc
|
| 5 |
import json
|
| 6 |
import os
|
| 7 |
import re
|
|
|
|
| 96 |
return model, processor
|
| 97 |
|
| 98 |
|
| 99 |
+
def release_bbox_bundle():
|
| 100 |
+
model = _BBOX_CACHE.get("model")
|
| 101 |
+
processor = _BBOX_CACHE.get("processor")
|
| 102 |
+
if model is not None:
|
| 103 |
+
del model
|
| 104 |
+
if processor is not None:
|
| 105 |
+
del processor
|
| 106 |
+
_BBOX_CACHE.update({"model_path": None, "model": None, "processor": None})
|
| 107 |
+
gc.collect()
|
| 108 |
+
if torch.cuda.is_available():
|
| 109 |
+
torch.cuda.empty_cache()
|
| 110 |
+
|
| 111 |
+
|
| 112 |
def load_real_bundle(config: dict):
|
| 113 |
key = (
|
| 114 |
config.get("pretrained_model_name_or_path"),
|
|
|
|
| 404 |
bbox_jsonl = write_bbox_jsonl(record, run_dir / "caption_bbox_infer.jsonl")
|
| 405 |
bbox_vis_path = run_dir / "bbox_vis" / f"{normalized_sample_name}_vis.png"
|
| 406 |
draw_boxes(prepared_image_path, bboxes, bbox_vis_path)
|
| 407 |
+
release_bbox_bundle()
|
| 408 |
|
| 409 |
config = build_runtime_config(
|
| 410 |
config_path=config_path,
|