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

Libraries

How to use statking/paligemma_vqa_lower with Transformers:

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

pipe = pipeline("image-text-to-text", model="statking/paligemma_vqa_lower")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("statking/paligemma_vqa_lower")
model = AutoModelForImageTextToText.from_pretrained("statking/paligemma_vqa_lower")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use statking/paligemma_vqa_lower with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/statking/paligemma_vqa_lower

SGLang

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

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

paligemma_vqa_lower

This model is a fine-tuned version of google/paligemma-3b-pt-224 on the vq_av2 dataset. It achieves the following results on the evaluation set:

Loss: 0.0122

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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 2
total_train_batch_size: 128
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 1200
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
4.837	0.1471	500	3.7992
0.1673	0.2943	1000	0.1149
0.0227	0.4414	1500	0.0198
0.0146	0.5886	2000	0.0138
0.0135	0.7357	2500	0.0125
0.013	0.8829	3000	0.0122

Framework versions

Transformers 4.41.0
Pytorch 2.2.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Downloads last month: 3

Safetensors

Model size

3B params

Tensor type

BF16

Inference Providers NEW

Image-Text-to-Text

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

Model tree for statking/paligemma_vqa_lower

Base model

google/paligemma-3b-pt-224

Finetuned

(78)

this model