Instructions to use MahsaShahidi/Persian-Image-Captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MahsaShahidi/Persian-Image-Captioning with Transformers:

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

pipe = pipeline("image-text-to-text", model="MahsaShahidi/Persian-Image-Captioning")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("MahsaShahidi/Persian-Image-Captioning")
model = AutoModelForMultimodalLM.from_pretrained("MahsaShahidi/Persian-Image-Captioning", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MahsaShahidi/Persian-Image-Captioning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MahsaShahidi/Persian-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": "MahsaShahidi/Persian-Image-Captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MahsaShahidi/Persian-Image-Captioning

SGLang

How to use MahsaShahidi/Persian-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 "MahsaShahidi/Persian-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": "MahsaShahidi/Persian-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 "MahsaShahidi/Persian-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": "MahsaShahidi/Persian-Image-Captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MahsaShahidi/Persian-Image-Captioning with Docker Model Runner:
```
docker model run hf.co/MahsaShahidi/Persian-Image-Captioning
```

Persian-Image-Captioning

Commit History

Jan 19, 2025

07:34
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
ef5402d

Feb 22, 2022

10:49
Update README.md

MahsaShahidi

30b2eb0

Feb 16, 2022

20:08
Update ReadMe.md

MahsaShahidi

91f5872
20:06
Added dataset name

MahsaShahidi

24eb6e4
19:42
update model card README.md

MahsaShahidi

817ba5f
19:32
Training in progress, step 28000

MahsaShahidi

48c45b2
18:35
Training in progress, step 21000

MahsaShahidi

ec4cdd6
17:39
Training in progress, step 14000

MahsaShahidi

e3da623
16:43
Training in progress, step 7000

MahsaShahidi

9484e68
15:40
initial commit

system HF Staff

b23ef22

Commit History

Jan 19, 2025

Adding `safetensors` variant of this model⁠

Feb 22, 2022

Update README.md

Feb 16, 2022

Update ReadMe.md

Added dataset name

update model card README.md

Training in progress, step 28000

Training in progress, step 21000

Training in progress, step 14000

Training in progress, step 7000

initial commit