Instructions to use Humayoun/Donut2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Humayoun/Donut2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Humayoun/Donut2")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("Humayoun/Donut2") model = AutoModelForMultimodalLM.from_pretrained("Humayoun/Donut2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Humayoun/Donut2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Humayoun/Donut2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Humayoun/Donut2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Humayoun/Donut2
- SGLang
How to use Humayoun/Donut2 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 "Humayoun/Donut2" \ --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": "Humayoun/Donut2", "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 "Humayoun/Donut2" \ --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": "Humayoun/Donut2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Humayoun/Donut2 with Docker Model Runner:
docker model run hf.co/Humayoun/Donut2
Training in progress, epoch 1
Browse files
config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"_commit_hash": "
|
| 3 |
-
"_name_or_path": "
|
| 4 |
"architectures": [
|
| 5 |
"VisionEncoderDecoderModel"
|
| 6 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_commit_hash": "a959cf33c20e09215873e338299c900f57047c61",
|
| 3 |
+
"_name_or_path": "naver-clova-ix/donut-base",
|
| 4 |
"architectures": [
|
| 5 |
"VisionEncoderDecoderModel"
|
| 6 |
],
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 809350937
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d923e26961665fdb90293af04720198472a1505e8e0a3b8b10062aeecd2c6041
|
| 3 |
size 809350937
|
runs/Feb27_12-03-52_0fc150968d36/1677499622.2662613/events.out.tfevents.1677499622.0fc150968d36.311.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dba791b9cec40fc25c89116451108f28eaa5616da2d0858590f239c465072cdd
|
| 3 |
+
size 5974
|
runs/Feb27_12-03-52_0fc150968d36/events.out.tfevents.1677499622.0fc150968d36.311.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46919ef847fad4ee5fb0ced45255f9f545cb48866d0ceba346201b6b7db0ceff
|
| 3 |
+
size 8398
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3707
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d325ccc62f03e12d72e92013aeffd444547ed99726484db6ff001897e551229a
|
| 3 |
size 3707
|