Instructions to use bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1")
model = AutoModelForMultimodalLM.from_pretrained("bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1

SGLang

How to use bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1 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 "bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1" \
    --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": "bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1",
		"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 "bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1" \
        --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": "bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1 with Docker Model Runner:
```
docker model run hf.co/bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1
```

NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1

This model is a fine-tuned version of MohamedRashad/arabic-small-nougat on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1782

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: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 6
total_train_batch_size: 48
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
1.7191	1.0	153	0.2669
1.3989	2.0	306	0.2178
1.1137	3.0	459	0.1958
0.8059	4.0	612	0.1855
0.8749	5.0	765	0.1809
0.7122	6.0	918	0.1774
0.4741	7.0	1071	0.1778
0.5197	8.0	1224	0.1779
0.58	9.0	1377	0.1772
0.5077	10.0	1530	0.1790
0.5602	11.0	1683	0.1785
0.5419	12.0	1836	0.1782

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu121
Datasets 3.6.0
Tokenizers 0.21.0

Downloads last month: 6

Safetensors

Model size

0.2B params

Tensor type

I64

BF16

Model tree for bustamiyusoef/NougatArabic_JawiAugment_MlyNewspaper_X_ransam1_v1

Base model

facebook/nougat-small

Finetuned

MohamedRashad/arabic-small-nougat

Finetuned

(3)

this model