Instructions to use PiotrSty/trocr-pl-mixed-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PiotrSty/trocr-pl-mixed-v2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="PiotrSty/trocr-pl-mixed-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("PiotrSty/trocr-pl-mixed-v2")
model = AutoModelForMultimodalLM.from_pretrained("PiotrSty/trocr-pl-mixed-v2", device_map="auto")

PEFT
How to use PiotrSty/trocr-pl-mixed-v2 with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PiotrSty/trocr-pl-mixed-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PiotrSty/trocr-pl-mixed-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PiotrSty/trocr-pl-mixed-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PiotrSty/trocr-pl-mixed-v2

SGLang

How to use PiotrSty/trocr-pl-mixed-v2 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 "PiotrSty/trocr-pl-mixed-v2" \
    --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": "PiotrSty/trocr-pl-mixed-v2",
		"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 "PiotrSty/trocr-pl-mixed-v2" \
        --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": "PiotrSty/trocr-pl-mixed-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PiotrSty/trocr-pl-mixed-v2 with Docker Model Runner:
```
docker model run hf.co/PiotrSty/trocr-pl-mixed-v2
```

PiotrSty/trocr-pl-mixed-v2 (experimental)

Longer fine-tune of PiotrSty/trocr-pl-base on synthetic Polish print + real EHRI typewritten Polish lines (CC-BY 4.0, ehri-pl-lines). Same recipe as trocr-pl-mixed-v1 (run 3) but 15 epochs instead of 5, because run 3's val CER was still falling at epoch 5.

Training

Base: PiotrSty/trocr-pl-base
Method: QLoRA on decoder attention (q/k/v/out_proj), rank 16, alpha 32
Train: 2000 synthetic lines + 349 real EHRI lines (3 docs)
Val: 38 EHRI lines (held-out doc ZIH3010905)
Epochs: 15, batch 8, lr 1e-4, T4 x2
Best checkpoint: /kaggle/working/trocr-pl-run4/checkpoint-1764 (val CER 0.3152, WER 0.7190)
Document-level split, no line leakage.

Evaluation on frozen held-out sets

Replace the numbers below with the actual run4 evaluation output from the notebook before publishing, or rerun training.evaluate on this model after download. Reference (run3 mixed-v1):

Model	EHRI test (81, typewriter)	real-lines-v1 (75, print)
trocr-pl-base (run2)	CER 47.30% / WER 90.82%	CER 11.11% / WER 35.84%
trocr-pl-mixed-v1 (run3, 5 ep)	CER 33.95% / WER 85.69%	CER 7.09% / WER 29.44%
trocr-pl-mixed-v2 (run4, 15 ep)	(fill from eval cell)	(fill from eval cell)

Limitations

Line recognizer only; page segmentation on faded typewriter is unreliable.
Only 349 real typewritten training lines.
Do NOT use as drop-in replacement without your own eval.

Provenance

See run.json, selection.json, best_metrics.json in this repo. Source: https://github.com/PiotrStyla/OCR_engine (commit 7065e6a) EHRI dataset: https://huggingface.co/datasets/PiotrSty/ehri-pl-lines

Downloads last month: 30

Safetensors

Model size

0.3B params

Tensor type

F32

Model tree for PiotrSty/trocr-pl-mixed-v2

Base model

microsoft/trocr-base-printed

Finetuned

PiotrSty/trocr-pl-base

Finetuned

(4)

this model