Instructions to use davanstrien/lightonocr-books-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use davanstrien/lightonocr-books-test with Transformers:

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

pipe = pipeline("text-generation", model="davanstrien/lightonocr-books-test")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("davanstrien/lightonocr-books-test", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use davanstrien/lightonocr-books-test with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/davanstrien/lightonocr-books-test

SGLang

How to use davanstrien/lightonocr-books-test 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 "davanstrien/lightonocr-books-test" \
    --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": "davanstrien/lightonocr-books-test",
		"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 "davanstrien/lightonocr-books-test" \
        --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": "davanstrien/lightonocr-books-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use davanstrien/lightonocr-books-test with Docker Model Runner:
```
docker model run hf.co/davanstrien/lightonocr-books-test
```

davanstrien HF Staff commited on Nov 4, 2025

Commit

2eb902f

verified ·

1 Parent(s): 6311f64

Model save

Browse files

Files changed (2) hide show

README.md +18 -18
model.safetensors +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [lightonai/LightOnOCR-1B-1025](https://huggingface.co/lightonai/LightOnOCR-1B-1025) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1889
 ## Model description
@@ -50,27 +50,27 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.9036        | 0.0619 | 50   | 0.2168          |
-| 0.7522        | 0.1239 | 100  | 0.2168          |
-| 0.7561        | 0.1858 | 150  | 0.2153          |
-| 0.8117        | 0.2478 | 200  | 0.2066          |
-| 0.7541        | 0.3097 | 250  | 0.2011          |
-| 0.6631        | 0.3716 | 300  | 0.2009          |
-| 0.7019        | 0.4336 | 350  | 0.1979          |
-| 0.853         | 0.4955 | 400  | 0.1953          |
-| 0.7941        | 0.5574 | 450  | 0.1914          |
-| 0.7765        | 0.6194 | 500  | 0.1901          |
-| 0.6321        | 0.6813 | 550  | 0.1915          |
-| 0.7474        | 0.7433 | 600  | 0.1900          |
-| 0.6291        | 0.8052 | 650  | 0.1887          |
-| 0.6896        | 0.8671 | 700  | 0.1892          |
-| 0.7958        | 0.9291 | 750  | 0.1896          |
-| 0.5989        | 0.9910 | 800  | 0.1889          |
 ### Framework versions
 - Transformers 5.0.0.dev0
 - Pytorch 2.9.0+cu128
-- Datasets 4.3.0
 - Tokenizers 0.22.1

 This model is a fine-tuned version of [lightonai/LightOnOCR-1B-1025](https://huggingface.co/lightonai/LightOnOCR-1B-1025) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.1898
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
+| 0.9005        | 0.0619 | 50   | 0.2190          |
+| 0.7568        | 0.1239 | 100  | 0.2133          |
+| 0.7556        | 0.1858 | 150  | 0.2129          |
+| 0.8055        | 0.2478 | 200  | 0.2108          |
+| 0.7609        | 0.3097 | 250  | 0.2021          |
+| 0.6656        | 0.3716 | 300  | 0.1993          |
+| 0.7036        | 0.4336 | 350  | 0.1979          |
+| 0.8552        | 0.4955 | 400  | 0.1929          |
+| 0.8087        | 0.5574 | 450  | 0.1944          |
+| 0.7815        | 0.6194 | 500  | 0.1913          |
+| 0.6349        | 0.6813 | 550  | 0.1930          |
+| 0.7542        | 0.7433 | 600  | 0.1901          |
+| 0.6332        | 0.8052 | 650  | 0.1913          |
+| 0.6949        | 0.8671 | 700  | 0.1904          |
+| 0.7974        | 0.9291 | 750  | 0.1896          |
+| 0.5963        | 0.9910 | 800  | 0.1898          |
 ### Framework versions
 - Transformers 5.0.0.dev0
 - Pytorch 2.9.0+cu128
+- Datasets 4.4.0
 - Tokenizers 0.22.1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53c713f68ec2205e7c9266cfbba678226d5f602e9a1632fba39262a193becec3
 size 2322532728

 version https://git-lfs.github.com/spec/v1
+oid sha256:13b469230d3d33c118f0c4fdd7ac6dbb8bf87c85e997eda5e2ea4b6f272ccd09
 size 2322532728