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")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("MahsaShahidi/Persian-Image-Captioning")
model = AutoModelForImageTextToText.from_pretrained("MahsaShahidi/Persian-Image-Captioning")

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
```

MahsaShahidi commited on Feb 16, 2022

Commit

91f5872

1 Parent(s): 24eb6e4

Update ReadMe.md

Browse files

Files changed (1) hide show

README.md +0 -11

README.md CHANGED Viewed

@@ -14,17 +14,6 @@ This model is a fine-tuned version of [Vision Encoder Decoder](https://huggingfa
 It achieves the following results on the evaluation set:
 - Loss: 2.4300
-## Model description
-More information needed
-## Intended uses & limitations
-More information needed
-## Training and evaluation data
-More information needed
 ## Training procedure

 It achieves the following results on the evaluation set:
 - Loss: 2.4300
 ## Training procedure