Instructions to use Nyaaneet/donut-base-ru_testing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nyaaneet/donut-base-ru_testing with Transformers:

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

pipe = pipeline("image-text-to-text", model="Nyaaneet/donut-base-ru_testing")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Nyaaneet/donut-base-ru_testing")
model = AutoModelForMultimodalLM.from_pretrained("Nyaaneet/donut-base-ru_testing")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Nyaaneet/donut-base-ru_testing with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Nyaaneet/donut-base-ru_testing

SGLang

How to use Nyaaneet/donut-base-ru_testing 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 "Nyaaneet/donut-base-ru_testing" \
    --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": "Nyaaneet/donut-base-ru_testing",
		"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 "Nyaaneet/donut-base-ru_testing" \
        --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": "Nyaaneet/donut-base-ru_testing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Nyaaneet/donut-base-ru_testing with Docker Model Runner:
```
docker model run hf.co/Nyaaneet/donut-base-ru_testing
```

Nyaaneet commited on Feb 14, 2023

Commit

43101f6

1 Parent(s): 27f6708

Training in progress, epoch 3

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Feb14_18-41-32_fbbe3adcb97c/events.out.tfevents.1676400120.fbbe3adcb97c.3455.0 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce78e8f41d4b9bbd516f94d9deb5eec7876f8c8bb15a73e79ad7878b8274a93d
 size 619603737

 version https://git-lfs.github.com/spec/v1
+oid sha256:82f7442c7a5875c4d136a5462139c04d77e2d05125d90723dabecbcce8c77b21
 size 619603737

runs/Feb14_18-41-32_fbbe3adcb97c/events.out.tfevents.1676400120.fbbe3adcb97c.3455.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81bf748b96536492710f77d79ea394577ba9f05ca7fa6b8deef16f1aead565cf
-size 9031

 version https://git-lfs.github.com/spec/v1
+oid sha256:9a175534971f58aa11bd9e1e18b2fda90f3d293ab05f8859f77c3ac82d0be976
+size 9502