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", device_map="auto")

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
```

NourFakih commited on May 1, 2024

Commit

c284282

verified ·

1 Parent(s): cc5d1dd

Training in progress, step 500

Browse files

Files changed (3) hide show

model.safetensors +1 -1
runs/May01_11-25-38_b47eb30dbf80/events.out.tfevents.1714562769.b47eb30dbf80.34.0 +3 -0
training_args.bin +1 -1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7d99eda5e1c86aed8e773c732c4ed535f9fa5c7494dc2d817e4ab19dec725e3
 size 956835520

 version https://git-lfs.github.com/spec/v1
+oid sha256:eb1350a690adf545db6544eec1d0bee8b2a840016587e2036f2212bd77a8b0a5
 size 956835520

runs/May01_11-25-38_b47eb30dbf80/events.out.tfevents.1714562769.b47eb30dbf80.34.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:25562e30faa5ba5fc908d95f77f26a1bae9142cef9d56c1a2df7bce31d7b91c5
+size 9808

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ee4194c46010c20856d2685f4fc1c098a9f98d8dcc0ed01e8186d0fcaae4d5c
 size 5112

 version https://git-lfs.github.com/spec/v1
+oid sha256:beb980215d30122c09a89b2599a3296b2e21cda08c1068c659a20c429fbc0117
 size 5112