Instructions to use majorSeaweed/BLIP-X_ray-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majorSeaweed/BLIP-X_ray-captioning with Transformers:

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

pipe = pipeline("image-text-to-text", model="majorSeaweed/BLIP-X_ray-captioning")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("majorSeaweed/BLIP-X_ray-captioning")
model = AutoModelForImageTextToText.from_pretrained("majorSeaweed/BLIP-X_ray-captioning")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use majorSeaweed/BLIP-X_ray-captioning with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/majorSeaweed/BLIP-X_ray-captioning

SGLang

How to use majorSeaweed/BLIP-X_ray-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 "majorSeaweed/BLIP-X_ray-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": "majorSeaweed/BLIP-X_ray-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 "majorSeaweed/BLIP-X_ray-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": "majorSeaweed/BLIP-X_ray-captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use majorSeaweed/BLIP-X_ray-captioning with Docker Model Runner:
```
docker model run hf.co/majorSeaweed/BLIP-X_ray-captioning
```

BLIP-X_ray-captioning / config.json

majorSeaweed

Upload BlipForConditionalGeneration

fe6479b verified 12 months ago

raw

history blame contribute delete

1.51 kB

	{
	"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,
	"attention_probs_dropout_prob": 0.0,
	"encoder_hidden_size": 768,
	"hidden_act": "gelu",
	"hidden_dropout_prob": 0.0,
	"hidden_size": 768,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"intermediate_size": 3072,
	"label_smoothing": 0.0,
	"layer_norm_eps": 1e-12,
	"max_position_embeddings": 512,
	"model_type": "blip_text_model",
	"num_attention_heads": 12,
	"num_hidden_layers": 12,
	"projection_dim": 768,
	"torch_dtype": "float32",
	"use_cache": true,
	"vocab_size": 30524
	},
	"torch_dtype": "float32",
	"transformers_version": "4.51.3",
	"vision_config": {
	"_attn_implementation_autoset": true,
	"attention_dropout": 0.0,
	"dropout": 0.0,
	"hidden_act": "gelu",
	"hidden_size": 768,
	"image_size": 384,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"intermediate_size": 3072,
	"layer_norm_eps": 1e-05,
	"model_type": "blip_vision_model",
	"num_attention_heads": 12,
	"num_channels": 3,
	"num_hidden_layers": 12,
	"patch_size": 16,
	"projection_dim": 512,
	"torch_dtype": "float32"
	}
	}