Instructions to use hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart with Transformers:

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

pipe = pipeline("image-text-to-text", model="hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart")
model = AutoModelForImageTextToText.from_pretrained("hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart

SGLang

How to use hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart 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 "hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart" \
    --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": "hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart",
		"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 "hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart" \
        --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": "hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart with Docker Model Runner:
```
docker model run hf.co/hf-internal-testing/tiny-random-VisionEncoderDecoderModel-donutswin-mbart
```

Xenova HF Staff commited on Oct 24, 2024

Commit

42aafa1

verified ·

1 Parent(s): 516ea9b

Upload model

Browse files

Files changed (2) hide show

config.json +4 -1
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -120,7 +120,10 @@
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
-    "image_size": 224,
     "initializer_range": 0.02,
     "is_decoder": false,
     "is_encoder_decoder": false,

       "0": "LABEL_0",
       "1": "LABEL_1"
     },
+    "image_size": [
+      2560,
+      1920
+    ],
     "initializer_range": 0.02,
     "is_decoder": false,
     "is_encoder_decoder": false,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c706f1405873012f46817ff5fd32e98f4e4b621fe07ef379c7472b4717a809cd
 size 28133944

 version https://git-lfs.github.com/spec/v1
+oid sha256:647d777e70d712619a6ae820a17425d7083830d50d5d4aab0c648c9a01a985fb
 size 28133944