Instructions to use RSRathore/ny-image-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RSRathore/ny-image-captioning with Transformers:

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

pipe = pipeline("image-text-to-text", model="RSRathore/ny-image-captioning")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("RSRathore/ny-image-captioning")
model = AutoModelForMultimodalLM.from_pretrained("RSRathore/ny-image-captioning", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RSRathore/ny-image-captioning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RSRathore/ny-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": "RSRathore/ny-image-captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RSRathore/ny-image-captioning

SGLang

How to use RSRathore/ny-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 "RSRathore/ny-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": "RSRathore/ny-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 "RSRathore/ny-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": "RSRathore/ny-image-captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RSRathore/ny-image-captioning with Docker Model Runner:
```
docker model run hf.co/RSRathore/ny-image-captioning
```

RSRathore commited on Apr 7, 2025

Commit

f81c508

verified ·

1 Parent(s): 0159c63

Upload BlipForConditionalGeneration

Browse files

Files changed (1) hide show

model.safetensors +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d07a28355e50b1f703391921ca62ae5c20e6a14ede8b56d08a3b3206cb349473
 size 989717056

 version https://git-lfs.github.com/spec/v1
+oid sha256:7d4f26da5563762d2129fb5aaf3d787daeb6349baac846fad954f11c72372aa1
 size 989717056