Instructions to use umarigan/vit-swin-base-224-gpt2-image-captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use umarigan/vit-swin-base-224-gpt2-image-captioning with Transformers:

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

pipe = pipeline("image-text-to-text", model="umarigan/vit-swin-base-224-gpt2-image-captioning")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("umarigan/vit-swin-base-224-gpt2-image-captioning")
model = AutoModelForImageTextToText.from_pretrained("umarigan/vit-swin-base-224-gpt2-image-captioning")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use umarigan/vit-swin-base-224-gpt2-image-captioning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "umarigan/vit-swin-base-224-gpt2-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": "umarigan/vit-swin-base-224-gpt2-image-captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/umarigan/vit-swin-base-224-gpt2-image-captioning

SGLang

How to use umarigan/vit-swin-base-224-gpt2-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 "umarigan/vit-swin-base-224-gpt2-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": "umarigan/vit-swin-base-224-gpt2-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 "umarigan/vit-swin-base-224-gpt2-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": "umarigan/vit-swin-base-224-gpt2-image-captioning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use umarigan/vit-swin-base-224-gpt2-image-captioning with Docker Model Runner:
```
docker model run hf.co/umarigan/vit-swin-base-224-gpt2-image-captioning
```

umarigan commited on Jul 9, 2025

Commit

e089421

verified ·

1 Parent(s): 2c852b9

umarigan/dreamoon

Browse files

Files changed (5) hide show

README.md +6 -6
model.safetensors +1 -1
runs/Jul09_08-56-44_fcc2f6f1de4a/events.out.tfevents.1752051411.fcc2f6f1de4a.4855.0 +3 -0
runs/Jul09_08-56-44_fcc2f6f1de4a/events.out.tfevents.1752057505.fcc2f6f1de4a.4855.1 +3 -0
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -17,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2740
-- Rouge1: 29.1967
-- Rouge2: 7.3414
-- Rougel: 23.013
-- Rougelsum: 23.0147
 - Bleu: 0.0
-- Gen Len: 33.1838
 ## Model description

 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.2164
+- Rouge1: 29.2983
+- Rouge2: 7.1349
+- Rougel: 22.7928
+- Rougelsum: 22.796
 - Bleu: 0.0
+- Gen Len: 32.3291
 ## Model description

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff8db5f45cfeef0c6f9810d3d2dc7e20cfbb4eb88982ed4771e19947db4de99
 size 961895704

 version https://git-lfs.github.com/spec/v1
+oid sha256:664da895a8d505e486891f13d766ee5f1d74e31e7d3ad160932db20c472aa66b
 size 961895704

runs/Jul09_08-56-44_fcc2f6f1de4a/events.out.tfevents.1752051411.fcc2f6f1de4a.4855.0 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:26e7e7c044bb808aefc721e35418d2af33d1631e8976ebb1453b62a300ef50fc
+size 1759365

runs/Jul09_08-56-44_fcc2f6f1de4a/events.out.tfevents.1752057505.fcc2f6f1de4a.4855.1 ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6224b0c2be9ae09df799a884866a690f8e1e7012b3cddda330ce57a63876b515
+size 661

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9532715010fef7222e08c75a3f02ef04020d3d66fb1bba646a49611f2c60c5b5
 size 5560

 version https://git-lfs.github.com/spec/v1
+oid sha256:69dd866959fa56bcfb3d60b9d46cd9e2ed836970732efbdef51b9c6bcdcf3d4f
 size 5560