Instructions to use bustamiyusoef/_Nougat_Base_Edv_En_De_01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bustamiyusoef/_Nougat_Base_Edv_En_De_01 with Transformers:

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

pipe = pipeline("image-text-to-text", model="bustamiyusoef/_Nougat_Base_Edv_En_De_01")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("bustamiyusoef/_Nougat_Base_Edv_En_De_01")
model = AutoModelForMultimodalLM.from_pretrained("bustamiyusoef/_Nougat_Base_Edv_En_De_01", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bustamiyusoef/_Nougat_Base_Edv_En_De_01 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bustamiyusoef/_Nougat_Base_Edv_En_De_01"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bustamiyusoef/_Nougat_Base_Edv_En_De_01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bustamiyusoef/_Nougat_Base_Edv_En_De_01

SGLang

How to use bustamiyusoef/_Nougat_Base_Edv_En_De_01 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/_Nougat_Base_Edv_En_De_01" \
    --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/_Nougat_Base_Edv_En_De_01",
		"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/_Nougat_Base_Edv_En_De_01" \
        --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/_Nougat_Base_Edv_En_De_01",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bustamiyusoef/_Nougat_Base_Edv_En_De_01 with Docker Model Runner:
```
docker model run hf.co/bustamiyusoef/_Nougat_Base_Edv_En_De_01
```

_Nougat_Base_Edv_En_De_01

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: 1700.0442

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: 10
total_train_batch_size: 80
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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	42	1.9061
22.7823	2.0	84	7.8791
68.1139	3.0	126	88.5974
829.2286	4.0	168	220.7463
2312.5455	5.0	210	283.3206
3190.685	6.0	252	408.0313
3190.685	7.0	294	772.9317
5969.3912	8.0	336	1039.8457
9675.3725	9.0	378	1248.5635
12223.905	10.0	420	1398.6156
14010.6213	11.0	462	1496.1117
15064.8962	12.0	504	1564.3519
15064.8962	13.0	546	1613.9442
15790.6938	14.0	588	1647.9702
16285.0438	15.0	630	1669.3680
16505.9075	16.0	672	1684.0092
16716.44	17.0	714	1693.2450
16915.6488	18.0	756	1698.5161
16915.6488	19.0	798	1699.9650
16804.3288	19.5251	820	1700.0442

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu121
Tokenizers 0.21.0

Downloads last month: 2

Safetensors

Model size

0.3B params

Tensor type

I64

BF16

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for bustamiyusoef/_Nougat_Base_Edv_En_De_01

Base model

facebook/nougat-base

Finetuned

(27)

this model