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

Libraries

How to use eduardo-bolognini/imagecaptioning with Transformers:

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

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

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("eduardo-bolognini/imagecaptioning")
model = AutoModelForImageTextToText.from_pretrained("eduardo-bolognini/imagecaptioning")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use eduardo-bolognini/imagecaptioning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eduardo-bolognini/imagecaptioning"
# 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/imagecaptioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use eduardo-bolognini/imagecaptioning 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/imagecaptioning" \
    --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/imagecaptioning",
		"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/imagecaptioning" \
        --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/imagecaptioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

eduardo-bolognini commited on Apr 27, 2025

Commit

73781cf

verified ·

1 Parent(s): 9176811

Upload BlipForConditionalGeneration

Browse files

Files changed (3) hide show

config.json +21 -3
generation_config.json +1 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "Salesforce/blip-image-captioning-large",
   "architectures": [
     "BlipForConditionalGeneration"
   ],
@@ -12,25 +11,44 @@
   "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"
   }
 }

 {
   "architectures": [
     "BlipForConditionalGeneration"
   ],
   "projection_dim": 512,
   "text_config": {
     "_attn_implementation_autoset": true,
+    "attention_probs_dropout_prob": 0.0,
     "encoder_hidden_size": 1024,
+    "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": 1024,
+    "image_size": 384,
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
     "intermediate_size": 4096,
+    "layer_norm_eps": 1e-05,
     "model_type": "blip_vision_model",
     "num_attention_heads": 16,
     "num_channels": 3,
     "num_hidden_layers": 24,
+    "patch_size": 16,
+    "projection_dim": 512,
     "torch_dtype": "float32"
   }
 }

generation_config.json CHANGED Viewed

@@ -3,5 +3,5 @@
   "bos_token_id": 30522,
   "eos_token_id": 2,
   "pad_token_id": 0,
-  "transformers_version": "4.49.0"
 }

   "bos_token_id": 30522,
   "eos_token_id": 2,
   "pad_token_id": 0,
+  "transformers_version": "4.51.3"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22a20097ca54964f9ea06c6a80fcdd13705d40defb30f864964659827fbbbeb8
 size 1879010480

 version https://git-lfs.github.com/spec/v1
+oid sha256:0de3db3affcab08f3c26f4a163b03709c52a1f16922dc88172cff015ed4c683e
 size 1879010480