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

Libraries

How to use JandC/donut-base-ner_small_memory with Transformers:

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

pipe = pipeline("image-text-to-text", model="JandC/donut-base-ner_small_memory")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("JandC/donut-base-ner_small_memory")
model = AutoModelForMultimodalLM.from_pretrained("JandC/donut-base-ner_small_memory")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JandC/donut-base-ner_small_memory with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/JandC/donut-base-ner_small_memory

SGLang

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

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

JandC commited on Nov 9, 2023

Commit

6579bf3

1 Parent(s): 160ab4d

Training in progress, epoch 10

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Nov09_00-14-08_bd08aa0616c1/events.out.tfevents.1699488862.bd08aa0616c1.1891.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa855289538be8e83853db91b60ba33bbbe5359df0a018db2a08ba8e2ea60ba8
 size 809177240

 version https://git-lfs.github.com/spec/v1
+oid sha256:dc5a515bbf0d0a2cca366d82a3236dc02763963f8d415d8acc8de026a66e3fff
 size 809177240

runs/Nov09_00-14-08_bd08aa0616c1/events.out.tfevents.1699488862.bd08aa0616c1.1891.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd94e1940b3ceaaa53e5296960b5279f876f56464458093b6f0ffc7cc44feff7
-size 65492

 version https://git-lfs.github.com/spec/v1
+oid sha256:7a882b234a9d7589e8794178bb7554111873a8da1d15fc186546a9bd19ee93a1
+size 72126