Instructions to use pchandragrid/blip-caption-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pchandragrid/blip-caption-model with Transformers:

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

pipe = pipeline("image-text-to-text", model="pchandragrid/blip-caption-model")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("pchandragrid/blip-caption-model")
model = AutoModelForImageTextToText.from_pretrained("pchandragrid/blip-caption-model")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pchandragrid/blip-caption-model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/pchandragrid/blip-caption-model

SGLang

How to use pchandragrid/blip-caption-model 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 "pchandragrid/blip-caption-model" \
    --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": "pchandragrid/blip-caption-model",
		"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 "pchandragrid/blip-caption-model" \
        --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": "pchandragrid/blip-caption-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pchandragrid/blip-caption-model with Docker Model Runner:
```
docker model run hf.co/pchandragrid/blip-caption-model
```

pchandragrid commited on Mar 5

Commit

ff9910b

verified ·

1 Parent(s): 07357b7

Upload processor

Browse files

Files changed (3) hide show

processor_config.json +27 -0
tokenizer.json +0 -0
tokenizer_config.json +21 -0

processor_config.json ADDED Viewed

	@@ -0,0 +1,27 @@

+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "BlipImageProcessorFast",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "height": 384,
+      "width": 384
+    }
+  },
+  "processor_class": "BlipProcessor"
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,21 @@

+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": true,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "processor_class": "BlipProcessor",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}