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

Libraries

How to use bustamiyusoef/_base_nougat_Char with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bustamiyusoef/_base_nougat_Char with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bustamiyusoef/_base_nougat_Char

SGLang

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

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

_base_nougat_JawiChar

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

Loss: 0.7218

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: 30

Training results

Training Loss	Epoch	Step	Validation Loss
21.3619	0.9783	15	1.7367
8.1981	1.9783	30	1.1706
6.7061	2.9783	45	1.0059
5.8689	3.9783	60	0.9978
5.9197	4.9783	75	0.9428
5.5444	5.9783	90	0.9029
5.4086	6.9783	105	0.8840
5.1521	7.9783	120	0.8626
5.2231	8.9783	135	0.8425
4.9312	9.9783	150	0.8164
4.8809	10.9783	165	0.8104
4.8759	11.9783	180	0.7843
4.9104	12.9783	195	0.7834
4.5906	13.9783	210	0.7732
4.5919	14.9783	225	0.7699
4.4027	15.9783	240	0.7521
4.5193	16.9783	255	0.7466
4.3829	17.9783	270	0.7603
4.2354	18.9783	285	0.7374
4.1685	19.9783	300	0.7435
4.2185	20.9783	315	0.7329
4.0828	21.9783	330	0.7311
4.1832	22.9783	345	0.7295
4.0023	23.9783	360	0.7237
4.0266	24.9783	375	0.7211
4.0373	25.9783	390	0.7233
4.0861	26.9783	405	0.7207
3.9774	27.9783	420	0.7193
4.1174	28.9783	435	0.7199
3.9658	29.9783	450	0.7218

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0

Downloads last month: 5

Safetensors

Model size

0.3B params

Tensor type

I64

BF16

Model tree for bustamiyusoef/_base_nougat_Char

Base model

facebook/nougat-base

Finetuned

(28)

this model

Finetunes

2 models