Instructions to use workwithHasnain/image-caption-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use workwithHasnain/image-caption-generator with Transformers:

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

pipe = pipeline("image-text-to-text", model="workwithHasnain/image-caption-generator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("workwithHasnain/image-caption-generator")
model = AutoModelForImageTextToText.from_pretrained("workwithHasnain/image-caption-generator")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use workwithHasnain/image-caption-generator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/workwithHasnain/image-caption-generator

SGLang

How to use workwithHasnain/image-caption-generator 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 "workwithHasnain/image-caption-generator" \
    --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": "workwithHasnain/image-caption-generator",
		"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 "workwithHasnain/image-caption-generator" \
        --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": "workwithHasnain/image-caption-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use workwithHasnain/image-caption-generator with Docker Model Runner:
```
docker model run hf.co/workwithHasnain/image-caption-generator
```

image-caption-generator

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

Loss: 0.2180

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: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 18

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	140	0.9561
No log	2.0	280	0.8228
No log	3.0	420	0.7362
1.0135	4.0	560	0.6639
1.0135	5.0	700	0.5998
1.0135	6.0	840	0.5435
1.0135	7.0	980	0.4893
0.6775	8.0	1120	0.4445
0.6775	9.0	1260	0.4032
0.6775	10.0	1400	0.3637
0.5059	11.0	1540	0.3269
0.5059	12.0	1680	0.3013
0.5059	13.0	1820	0.2749
0.5059	14.0	1960	0.2553
0.389	15.0	2100	0.2395
0.389	16.0	2240	0.2280
0.389	17.0	2380	0.2214
0.3218	18.0	2520	0.2180

Framework versions

Transformers 4.39.3
Pytorch 2.1.2
Datasets 2.18.0
Tokenizers 0.15.2

Downloads last month: 2

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