Instructions to use circulus/vit-roberta-caption-ko-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use circulus/vit-roberta-caption-ko-v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="circulus/vit-roberta-caption-ko-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("circulus/vit-roberta-caption-ko-v1")
model = AutoModelForImageTextToText.from_pretrained("circulus/vit-roberta-caption-ko-v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use circulus/vit-roberta-caption-ko-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "circulus/vit-roberta-caption-ko-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "circulus/vit-roberta-caption-ko-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/circulus/vit-roberta-caption-ko-v1

SGLang

How to use circulus/vit-roberta-caption-ko-v1 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 "circulus/vit-roberta-caption-ko-v1" \
    --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": "circulus/vit-roberta-caption-ko-v1",
		"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 "circulus/vit-roberta-caption-ko-v1" \
        --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": "circulus/vit-roberta-caption-ko-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use circulus/vit-roberta-caption-ko-v1 with Docker Model Runner:
```
docker model run hf.co/circulus/vit-roberta-caption-ko-v1
```

rippertnt commited on Sep 12, 2022

Commit

8fa983a

1 Parent(s): a619fd1

add model

Browse files

Files changed (1) hide show

preprocessor_config.json +17 -0

preprocessor_config.json ADDED Viewed

	@@ -0,0 +1,17 @@

+{
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "ViTFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "size": 224
+}