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

Libraries

How to use Zekrompogu/apnrpajak with Transformers:

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

pipe = pipeline("image-text-to-text", model="Zekrompogu/apnrpajak")

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

tokenizer = AutoTokenizer.from_pretrained("Zekrompogu/apnrpajak")
model = AutoModelForMultimodalLM.from_pretrained("Zekrompogu/apnrpajak", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Zekrompogu/apnrpajak with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Zekrompogu/apnrpajak

SGLang

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

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

microsoft/trocr-base-str

This model is a fine-tuned version of microsoft/trocr-base-str on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.1827
Cer: 0.0133
Wer: 0.0367

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: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 25
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
3.4122	1.0	44	0.4408	0.0733	0.1567
0.2502	2.0	88	0.1648	0.0167	0.0367
0.0886	3.0	132	0.1456	0.0108	0.03
0.0622	4.0	176	0.1488	0.0100	0.03
0.0314	5.0	220	0.1503	0.0100	0.03
0.0264	6.0	264	0.1513	0.0108	0.03
0.0177	7.0	308	0.1457	0.0108	0.03
0.0133	8.0	352	0.1498	0.0108	0.03
0.006	9.0	396	0.1583	0.0108	0.03
0.0051	10.0	440	0.1633	0.0125	0.0333
0.0027	11.0	484	0.1708	0.0117	0.0333
0.005	12.0	528	0.1703	0.0108	0.0333
0.0015	13.0	572	0.1750	0.0108	0.03
0.0021	14.0	616	0.1726	0.0117	0.0333
0.0004	15.0	660	0.1736	0.0108	0.03
0.0007	16.0	704	0.1741	0.0125	0.0367
0.0004	17.0	748	0.1849	0.0125	0.0367
0.0008	18.0	792	0.1850	0.0133	0.0367
0.0003	19.0	836	0.1837	0.0117	0.0367
0.0003	20.0	880	0.1848	0.0133	0.0367
0.0002	21.0	924	0.1836	0.0133	0.0367
0.0002	22.0	968	0.1835	0.0133	0.0367
0.0005	23.0	1012	0.1829	0.0133	0.0367
0.0002	24.0	1056	0.1826	0.0133	0.0367
0.0002	25.0	1100	0.1827	0.0133	0.0367

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 2.17.0
Tokenizers 0.19.1

Downloads last month: 3

Safetensors

Model size

0.3B params

Tensor type

F32

Model tree for Zekrompogu/apnrpajak

Base model

microsoft/trocr-base-str

Finetuned

(11)

this model