Instructions to use aquaqamelob/LightOnOCR-2-1B-pl-pdf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use aquaqamelob/LightOnOCR-2-1B-pl-pdf with PEFT:
```
Task type is invalid.
```

How to use aquaqamelob/LightOnOCR-2-1B-pl-pdf with Transformers:

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

pipe = pipeline("text-generation", model="aquaqamelob/LightOnOCR-2-1B-pl-pdf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("aquaqamelob/LightOnOCR-2-1B-pl-pdf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aquaqamelob/LightOnOCR-2-1B-pl-pdf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aquaqamelob/LightOnOCR-2-1B-pl-pdf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aquaqamelob/LightOnOCR-2-1B-pl-pdf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aquaqamelob/LightOnOCR-2-1B-pl-pdf

SGLang

How to use aquaqamelob/LightOnOCR-2-1B-pl-pdf 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 "aquaqamelob/LightOnOCR-2-1B-pl-pdf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aquaqamelob/LightOnOCR-2-1B-pl-pdf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "aquaqamelob/LightOnOCR-2-1B-pl-pdf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aquaqamelob/LightOnOCR-2-1B-pl-pdf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aquaqamelob/LightOnOCR-2-1B-pl-pdf with Docker Model Runner:
```
docker model run hf.co/aquaqamelob/LightOnOCR-2-1B-pl-pdf
```

LightOnOCR-2-ft-polish_pdf

This model is a fine-tuned version of lightonai/LightOnOCR-2-1B on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0080

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 4e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.05
training_steps: 250

Training results

Training Loss	Epoch	Step	Validation Loss
0.0301	0.3137	50	0.0162
0.0069	0.6275	100	0.0090
0.0108	0.9412	150	0.0083
0.0070	1.2510	200	0.0081
0.0145	1.5647	250	0.0080

Framework versions

PEFT 0.19.1
Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.8.5
Tokenizers 0.22.2

Downloads last month: -

Model tree for aquaqamelob/LightOnOCR-2-1B-pl-pdf

Base model

lightonai/LightOnOCR-2-1B

Adapter

(7)

this model