Instructions to use staghado/lightonocr-ft-iam-1ep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use staghado/lightonocr-ft-iam-1ep with Transformers:

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

pipe = pipeline("text-generation", model="staghado/lightonocr-ft-iam-1ep")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("staghado/lightonocr-ft-iam-1ep", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use staghado/lightonocr-ft-iam-1ep with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/staghado/lightonocr-ft-iam-1ep

SGLang

How to use staghado/lightonocr-ft-iam-1ep 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 "staghado/lightonocr-ft-iam-1ep" \
    --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": "staghado/lightonocr-ft-iam-1ep",
		"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 "staghado/lightonocr-ft-iam-1ep" \
        --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": "staghado/lightonocr-ft-iam-1ep",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use staghado/lightonocr-ft-iam-1ep with Docker Model Runner:
```
docker model run hf.co/staghado/lightonocr-ft-iam-1ep
```

lightonocr-ft-iam-1ep

This model is a fine-tuned version of lightonai/LightOnOCR-1B-1025 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1344

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: 6e-05
train_batch_size: 8
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
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: 10
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.4848	0.3322	100	0.2298
0.3688	0.6645	200	0.1673
0.3001	0.9967	300	0.1429
0.1099	1.3289	400	0.1361
0.1136	1.6611	500	0.1348
0.1169	1.9934	600	0.1344

Framework versions

Transformers 5.0.0.dev0
Pytorch 2.9.0+cu128
Datasets 4.3.0
Tokenizers 0.22.1

Downloads last month: 5

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for staghado/lightonocr-ft-iam-1ep

Base model

lightonai/LightOnOCR-1B-1025

Finetuned

(6)

this model