Instructions to use Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k with Transformers:

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

pipe = pipeline("image-text-to-text", model="Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k")
model = AutoModelForMultimodalLM.from_pretrained("Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k

SGLang

How to use Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k 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 "Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k" \
    --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": "Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k",
		"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 "Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k" \
        --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": "Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k with Docker Model Runner:
```
docker model run hf.co/Image-Captioning-ML/image-captioning-Vit-GPT2-Flickr8k
```

help

by here4code - opened Apr 8, 2025

Discussion

here4code

Apr 8, 2025

I , I have the Flickr dataset same one u used but I have caption in Hindi language not in English
can u help me train

NourFakih

Image-Captioning-ML org Apr 19, 2025

Hi! The code I utilized is available in the original model repository. This model was fine-tuned from nlpconnect/vit-gpt2-image-captioning, and you can refer to their official blog post for a comprehensive walkthrough and training code. This should assist you in fine-tuning the model with your Hindi captions.
https://ankur3107.github.io/blogs/the-illustrated-image-captioning-using-transformers/

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment