Instructions to use sihoon00/Bitamin_mutimodal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sihoon00/Bitamin_mutimodal with Transformers:

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

pipe = pipeline("image-text-to-text", model="sihoon00/Bitamin_mutimodal")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("sihoon00/Bitamin_mutimodal")
model = AutoModelForImageTextToText.from_pretrained("sihoon00/Bitamin_mutimodal")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sihoon00/Bitamin_mutimodal with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sihoon00/Bitamin_mutimodal"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sihoon00/Bitamin_mutimodal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sihoon00/Bitamin_mutimodal

SGLang

How to use sihoon00/Bitamin_mutimodal 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 "sihoon00/Bitamin_mutimodal" \
    --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": "sihoon00/Bitamin_mutimodal",
		"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 "sihoon00/Bitamin_mutimodal" \
        --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": "sihoon00/Bitamin_mutimodal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sihoon00/Bitamin_mutimodal with Docker Model Runner:
```
docker model run hf.co/sihoon00/Bitamin_mutimodal
```

Bitamin_mutimodal

This model is a fine-tuned version of ddobokki/vision-encoder-decoder-vit-gpt2-coco-ko on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0644
Rouge1: 6.6906
Rouge2: 3.2986
Rougel: 6.6499
Rougelsum: 6.6803
Gen Len: 100.0

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: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.2001	1.0	2982	0.1589	0.0	0.0	0.0	0.0	100.0
0.1178	2.0	5964	0.1095	0.8554	0.7275	0.8315	0.8554	100.0
0.0778	3.0	8946	0.0829	2.7168	1.6458	2.7157	2.6864	100.0
0.0552	4.0	11928	0.0691	5.454	2.6068	5.4184	5.4101	100.0
0.0396	5.0	14910	0.0644	6.6906	3.2986	6.6499	6.6803	100.0

Framework versions

Transformers 4.42.3
Pytorch 2.1.2
Datasets 2.20.0
Tokenizers 0.19.1

Downloads last month: 4

Safetensors

Model size

0.2B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

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