Instructions to use lmajnaric/paligemma-architecture-styles with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lmajnaric/paligemma-architecture-styles with Transformers:

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

pipe = pipeline("image-text-to-text", model="lmajnaric/paligemma-architecture-styles")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("lmajnaric/paligemma-architecture-styles")
model = AutoModelForMultimodalLM.from_pretrained("lmajnaric/paligemma-architecture-styles", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lmajnaric/paligemma-architecture-styles with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/lmajnaric/paligemma-architecture-styles

SGLang

How to use lmajnaric/paligemma-architecture-styles 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 "lmajnaric/paligemma-architecture-styles" \
    --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": "lmajnaric/paligemma-architecture-styles",
		"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 "lmajnaric/paligemma-architecture-styles" \
        --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": "lmajnaric/paligemma-architecture-styles",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lmajnaric/paligemma-architecture-styles with Docker Model Runner:
```
docker model run hf.co/lmajnaric/paligemma-architecture-styles
```

paligemma-architecture-styles

This model is a fine-tuned version of google/paligemma2-3b-pt-448 on the None dataset.

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: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 20
num_epochs: 3

Training results

TrainOutput(global_step=261, training_loss=1.761135561912681, metrics={'train_runtime': 1063.4627, 'train_samples_per_second': 1.975, 'train_steps_per_second': 0.245, 'total_flos': 3.156513684279552e+16, 'train_loss': 1.761135561912681, 'epoch': 2.9714285714285715})

Evals on base vs fine-tune

Base model:

Evaluation complete - Accuracy: 0.2400 (240/1000)

Performance by style: Ancient Egyptian architecture: 0.09 (5/57) Art Deco architecture: 0.23 (17/75) Art Nouveau architecture: 0.01 (1/73) Baroque architecture: 0.26 (15/58) Bauhaus architecture: 0.00 (0/58) Brutalism: 0.00 (0/38) Byzantine architecture: 0.34 (17/50) Chicago school architecture: 0.06 (3/51) Colonial architecture: 0.30 (27/89) Deconstructivism: 0.00 (0/38) Gothic architecture: 0.98 (59/60) Greek Revival architecture: 0.45 (26/58) International style: 0.00 (0/66) Neoclassicism: 0.14 (18/125) Postmodern architecture: 0.94 (47/50) Romanesque architecture: 0.09 (5/54) Base model results saved to paligemma448_arch_finetune_styles/base_model_folder_eval_20250316_183525.csv

=== EVALUATION RESULTS COMPARISON === Fine-tuned model accuracy: 0.8440 Base model accuracy: 0.2400 Improvement: 0.6040

The checkpoint-176 performs better than the latest checkpoint by .02, even though the training loss is lower on the latest checkpoint.

Framework versions

Transformers 4.50.0.dev0
Pytorch 2.6.0+cu124
Datasets 3.4.0
Tokenizers 0.21.0

Downloads last month: 8

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 lmajnaric/paligemma-architecture-styles

Base model

google/paligemma2-3b-pt-448

Finetuned

(42)

this model