Instructions to use cyttic/trocr-small-BY5-stage1-baseline with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cyttic/trocr-small-BY5-stage1-baseline with Transformers:

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

pipe = pipeline("image-text-to-text", model="cyttic/trocr-small-BY5-stage1-baseline")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("cyttic/trocr-small-BY5-stage1-baseline")
model = AutoModelForMultimodalLM.from_pretrained("cyttic/trocr-small-BY5-stage1-baseline", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cyttic/trocr-small-BY5-stage1-baseline with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cyttic/trocr-small-BY5-stage1-baseline"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cyttic/trocr-small-BY5-stage1-baseline",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cyttic/trocr-small-BY5-stage1-baseline

SGLang

How to use cyttic/trocr-small-BY5-stage1-baseline 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 "cyttic/trocr-small-BY5-stage1-baseline" \
    --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": "cyttic/trocr-small-BY5-stage1-baseline",
		"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 "cyttic/trocr-small-BY5-stage1-baseline" \
        --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": "cyttic/trocr-small-BY5-stage1-baseline",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cyttic/trocr-small-BY5-stage1-baseline with Docker Model Runner:
```
docker model run hf.co/cyttic/trocr-small-BY5-stage1-baseline
```

trocr-small-BY5-stage1-baseline

This model is a fine-tuned version of cyttic/trocr-hebrew-small-untrained on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 6.0938
Cer: 0.7764
Wer: 1.2183

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
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: linear
lr_scheduler_warmup_steps: 1550
num_epochs: 1.0
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
13.4280	0.1290	2000	6.5431	0.8336	1.3404
12.6550	0.2581	4000	6.3343	0.7790	1.1704
12.8663	0.3871	6000	6.2829	0.8043	1.2783
12.6129	0.5161	8000	6.1883	0.7629	1.1179
12.4563	0.6452	10000	6.1467	0.7787	1.1391
12.6108	0.7742	12000	6.1222	0.7870	1.1703
12.5069	0.9032	14000	6.1029	0.7804	1.2303
12.2563	1.0	15500	6.0938	0.7764	1.2183

Framework versions

Transformers 5.15.0
Pytorch 2.10.0+cu128
Datasets 5.0.1
Tokenizers 0.22.2

Downloads last month: 25

Safetensors

Model size

0.2B params

Tensor type

F32

Model tree for cyttic/trocr-small-BY5-stage1-baseline

Base model

cyttic/trocr-hebrew-small-untrained

Finetuned

(6)

this model