Instructions to use raxtemur/RuTrOCR_Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use raxtemur/RuTrOCR_Base with Transformers:

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

pipe = pipeline("image-text-to-text", model="raxtemur/RuTrOCR_Base")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("raxtemur/RuTrOCR_Base")
model = AutoModelForMultimodalLM.from_pretrained("raxtemur/RuTrOCR_Base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use raxtemur/RuTrOCR_Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "raxtemur/RuTrOCR_Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "raxtemur/RuTrOCR_Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/raxtemur/RuTrOCR_Base

SGLang

How to use raxtemur/RuTrOCR_Base 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 "raxtemur/RuTrOCR_Base" \
    --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": "raxtemur/RuTrOCR_Base",
		"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 "raxtemur/RuTrOCR_Base" \
        --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": "raxtemur/RuTrOCR_Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use raxtemur/RuTrOCR_Base with Docker Model Runner:
```
docker model run hf.co/raxtemur/RuTrOCR_Base
```

RuTrOCR_Base

Commit History

Jan 26, 2025

19:03
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
8bbbe40

Mar 20, 2024

10:14
Create README.md

raxtemur

Verified signature
6f56291
10:09
Upload model, epoch 187 (about a week on 2xA100(80))

raxtemur

Verified signature
72d7dd6
10:08
Upload processor

raxtemur

Verified signature
590978d
10:01
initial commit

raxtemur

Verified signature
2471fc6

Commit History

Jan 26, 2025

Adding `safetensors` variant of this model⁠

Mar 20, 2024

Create README.md

Upload model, epoch 187 (about a week on 2xA100(80))

Upload processor

initial commit