Instructions to use eduardo-bolognini/image_captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eduardo-bolognini/image_captioning with Transformers:

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

pipe = pipeline("image-text-to-text", model="eduardo-bolognini/image_captioning")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("eduardo-bolognini/image_captioning")
model = AutoModelForMultimodalLM.from_pretrained("eduardo-bolognini/image_captioning", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use eduardo-bolognini/image_captioning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eduardo-bolognini/image_captioning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eduardo-bolognini/image_captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/eduardo-bolognini/image_captioning

SGLang

How to use eduardo-bolognini/image_captioning 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 "eduardo-bolognini/image_captioning" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eduardo-bolognini/image_captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "eduardo-bolognini/image_captioning" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eduardo-bolognini/image_captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use eduardo-bolognini/image_captioning with Docker Model Runner:
```
docker model run hf.co/eduardo-bolognini/image_captioning
```

image_captioning / config.json

eduardo-bolognini

Upload BlipForConditionalGeneration

1717ac6 verified over 1 year ago

Raw History Blame Contribute Delete

975 Bytes

{
  "_name_or_path": "Salesforce/blip-image-captioning-large",
  "architectures": [
    "BlipForConditionalGeneration"
  ],
  "image_text_hidden_size": 256,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "label_smoothing": 0.0,
  "logit_scale_init_value": 2.6592,
  "model_type": "blip",
  "projection_dim": 512,
  "text_config": {
    "_attn_implementation_autoset": true,
    "encoder_hidden_size": 1024,
    "initializer_factor": 1.0,
    "model_type": "blip_text_model",
    "num_attention_heads": 12,
    "torch_dtype": "float32"
  },
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "vision_config": {
    "_attn_implementation_autoset": true,
    "dropout": 0.0,
    "hidden_size": 1024,
    "initializer_factor": 1.0,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "model_type": "blip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "torch_dtype": "float32"
  }
}

	{
	"_name_or_path": "Salesforce/blip-image-captioning-large",
	"architectures": [
	"BlipForConditionalGeneration"
	],
	"image_text_hidden_size": 256,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"label_smoothing": 0.0,
	"logit_scale_init_value": 2.6592,
	"model_type": "blip",
	"projection_dim": 512,
	"text_config": {
	"_attn_implementation_autoset": true,
	"encoder_hidden_size": 1024,
	"initializer_factor": 1.0,
	"model_type": "blip_text_model",
	"num_attention_heads": 12,
	"torch_dtype": "float32"
	},
	"torch_dtype": "float32",
	"transformers_version": "4.49.0",
	"vision_config": {
	"_attn_implementation_autoset": true,
	"dropout": 0.0,
	"hidden_size": 1024,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"model_type": "blip_vision_model",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 24,
	"torch_dtype": "float32"
	}
	}