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
File size: 2,543 Bytes
205434c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 | {
"additional_special_tokens": [
"<extra_id_0>",
"<extra_id_1>",
"<extra_id_2>",
"<extra_id_3>",
"<extra_id_4>",
"<extra_id_5>",
"<extra_id_6>",
"<extra_id_7>",
"<extra_id_8>",
"<extra_id_9>",
"<extra_id_10>",
"<extra_id_11>",
"<extra_id_12>",
"<extra_id_13>",
"<extra_id_14>",
"<extra_id_15>",
"<extra_id_16>",
"<extra_id_17>",
"<extra_id_18>",
"<extra_id_19>",
"<extra_id_20>",
"<extra_id_21>",
"<extra_id_22>",
"<extra_id_23>",
"<extra_id_24>",
"<extra_id_25>",
"<extra_id_26>",
"<extra_id_27>",
"<extra_id_28>",
"<extra_id_29>",
"<extra_id_30>",
"<extra_id_31>",
"<extra_id_32>",
"<extra_id_33>",
"<extra_id_34>",
"<extra_id_35>",
"<extra_id_36>",
"<extra_id_37>",
"<extra_id_38>",
"<extra_id_39>",
"<extra_id_40>",
"<extra_id_41>",
"<extra_id_42>",
"<extra_id_43>",
"<extra_id_44>",
"<extra_id_45>",
"<extra_id_46>",
"<extra_id_47>",
"<extra_id_48>",
"<extra_id_49>",
"<extra_id_50>",
"<extra_id_51>",
"<extra_id_52>",
"<extra_id_53>",
"<extra_id_54>",
"<extra_id_55>",
"<extra_id_56>",
"<extra_id_57>",
"<extra_id_58>",
"<extra_id_59>",
"<extra_id_60>",
"<extra_id_61>",
"<extra_id_62>",
"<extra_id_63>",
"<extra_id_64>",
"<extra_id_65>",
"<extra_id_66>",
"<extra_id_67>",
"<extra_id_68>",
"<extra_id_69>",
"<extra_id_70>",
"<extra_id_71>",
"<extra_id_72>",
"<extra_id_73>",
"<extra_id_74>",
"<extra_id_75>",
"<extra_id_76>",
"<extra_id_77>",
"<extra_id_78>",
"<extra_id_79>",
"<extra_id_80>",
"<extra_id_81>",
"<extra_id_82>",
"<extra_id_83>",
"<extra_id_84>",
"<extra_id_85>",
"<extra_id_86>",
"<extra_id_87>",
"<extra_id_88>",
"<extra_id_89>",
"<extra_id_90>",
"<extra_id_91>",
"<extra_id_92>",
"<extra_id_93>",
"<extra_id_94>",
"<extra_id_95>",
"<extra_id_96>",
"<extra_id_97>",
"<extra_id_98>",
"<extra_id_99>"
],
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}
|