Instructions to use LuongNam/ppy-doc-parser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LuongNam/ppy-doc-parser with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="LuongNam/ppy-doc-parser")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("LuongNam/ppy-doc-parser") model = AutoModelForImageTextToText.from_pretrained("LuongNam/ppy-doc-parser") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use LuongNam/ppy-doc-parser with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LuongNam/ppy-doc-parser" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LuongNam/ppy-doc-parser", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LuongNam/ppy-doc-parser
- SGLang
How to use LuongNam/ppy-doc-parser 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 "LuongNam/ppy-doc-parser" \ --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": "LuongNam/ppy-doc-parser", "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 "LuongNam/ppy-doc-parser" \ --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": "LuongNam/ppy-doc-parser", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LuongNam/ppy-doc-parser with Docker Model Runner:
docker model run hf.co/LuongNam/ppy-doc-parser
Commit ·
8e2d66b
1
Parent(s): a4e562a
Training in progress, epoch 0
Browse files- config.json +2 -2
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "LuongNam/
|
| 3 |
"architectures": [
|
| 4 |
"VisionEncoderDecoderModel"
|
| 5 |
],
|
|
@@ -87,7 +87,7 @@
|
|
| 87 |
"use_cache": true,
|
| 88 |
"vocab_size": 64071
|
| 89 |
},
|
| 90 |
-
"decoder_start_token_id":
|
| 91 |
"encoder": {
|
| 92 |
"_name_or_path": "",
|
| 93 |
"add_cross_attention": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "LuongNam/donut-ocr-vn-tokenizer",
|
| 3 |
"architectures": [
|
| 4 |
"VisionEncoderDecoderModel"
|
| 5 |
],
|
|
|
|
| 87 |
"use_cache": true,
|
| 88 |
"vocab_size": 64071
|
| 89 |
},
|
| 90 |
+
"decoder_start_token_id": 0,
|
| 91 |
"encoder": {
|
| 92 |
"_name_or_path": "",
|
| 93 |
"add_cross_attention": false,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 835883160
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19384c248bd5c39439e852a1ec2ac65a7be69bb41921acf6cc76e40eb99d0420
|
| 3 |
size 835883160
|