Instructions to use Ba2han/Liquid-Turkish-MiniOCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ba2han/Liquid-Turkish-MiniOCR with Transformers:

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

pipe = pipeline("image-text-to-text", model="Ba2han/Liquid-Turkish-MiniOCR")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Ba2han/Liquid-Turkish-MiniOCR")
model = AutoModelForImageTextToText.from_pretrained("Ba2han/Liquid-Turkish-MiniOCR")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ba2han/Liquid-Turkish-MiniOCR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ba2han/Liquid-Turkish-MiniOCR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/Liquid-Turkish-MiniOCR",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Ba2han/Liquid-Turkish-MiniOCR

SGLang

How to use Ba2han/Liquid-Turkish-MiniOCR 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 "Ba2han/Liquid-Turkish-MiniOCR" \
    --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": "Ba2han/Liquid-Turkish-MiniOCR",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "Ba2han/Liquid-Turkish-MiniOCR" \
        --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": "Ba2han/Liquid-Turkish-MiniOCR",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Unsloth Studio new

How to use Ba2han/Liquid-Turkish-MiniOCR with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ba2han/Liquid-Turkish-MiniOCR to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Ba2han/Liquid-Turkish-MiniOCR to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ba2han/Liquid-Turkish-MiniOCR to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Ba2han/Liquid-Turkish-MiniOCR",
    max_seq_length=2048,
)

Docker Model Runner
How to use Ba2han/Liquid-Turkish-MiniOCR with Docker Model Runner:
```
docker model run hf.co/Ba2han/Liquid-Turkish-MiniOCR
```

Example Script/Örnek Script

from transformers import pipeline

# ── Config ──
model_name = "Ba2han/Liquid-Turkish-MiniOCR"
image_url  = "https://gezivita.com/wp-content/uploads/2017/10/Atat%C3%BCrk-diyor-ki.jpg"

# ── Pipeline ──
pipe = pipeline("image-text-to-text", model=model_name)

messages = [{"role": "user", "content": [
    {"type": "image", "url": image_url},
    {"type": "text",  "text": "Görev: Türkçe OCR"},
]}]

result = pipe(text=messages, max_new_tokens=500, return_full_text=False,
              do_sample=True, temperature=0.3, top_k=10, min_p=0.2,
              repetition_penalty=1.05)

print(result[0]["generated_text"])

Result/Sonuç

CUMHURİYET

Cumhuriyet ahlâkî fazilete müstenit bir idaredir. Cumhuriyet fazilettir. Sultanlık korku ve tehdide müstenit bir idaredir. Cumhuriyet idaresi faziletti ve namuskâr insanlar yetiştirir, sultanlık korkuya, tehdide müstenit olduğu için korkak, zelil, sefil, rezil insanlar yetiştirir. (14 Ekim 1925)

Şuur daima ileriye ve yeniliğe götürür, dönüşsüz bir haslet olduğuna göre, Türkiye Cumhuriyeti halkı, ileriye ve yeniliğe uzun adımlarla yürümeye devam edecektir. (1.9.1925)

Memnuniyetle tekrar görüyorum ki, Lâik Cumhuriyet esasında beraberiz. Zaten benim siyasi hayatta bir taraflı olarak daima aradığım ve arıyacağım temel budur. (11.3.1930)

Benim naçiz vücudum elbet birgün toprak olacaktır. Fakat Türkiye Cumhuriyeti ilelebet pâyidâr kalacaktır. (Mayıs 1929)

Türk Milletinin tabiat ve şiârına en mutabık (uygun) olan idare Cumhuriyet idaresidir. (1924)

Usage/Kullanım

Görevin, sana verilen sayfadaki tüm içeriği eğitim materyali standartlarına uygun, eksiksiz ve dijital olarak okunabilir bir metne dönüştürmektir.

Görev: Türkçe OCR

Türkçe dilindeki sayfayı transkribe et. Formatı korumak adına markdown kullan.

Uploaded model

Developed by: Ba2han
License: apache-2.0
Finetuned from model : LiquidAI/LFM2.5-VL-1.6B

This lfm2_vl model was trained 2x faster with Unsloth

Downloads last month: 9

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for Ba2han/Liquid-Turkish-MiniOCR

Base model

LiquidAI/LFM2.5-1.2B-Base

Finetuned

LiquidAI/LFM2.5-VL-1.6B

Finetuned

(7)

this model