Instructions to use nanom/paligemma-3b-224-ft-vizwiztxtvqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nanom/paligemma-3b-224-ft-vizwiztxtvqa with Transformers:

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

pipe = pipeline("image-text-to-text", model="nanom/paligemma-3b-224-ft-vizwiztxtvqa")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("nanom/paligemma-3b-224-ft-vizwiztxtvqa")
model = AutoModelForMultimodalLM.from_pretrained("nanom/paligemma-3b-224-ft-vizwiztxtvqa", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nanom/paligemma-3b-224-ft-vizwiztxtvqa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nanom/paligemma-3b-224-ft-vizwiztxtvqa"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nanom/paligemma-3b-224-ft-vizwiztxtvqa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nanom/paligemma-3b-224-ft-vizwiztxtvqa

SGLang

How to use nanom/paligemma-3b-224-ft-vizwiztxtvqa 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 "nanom/paligemma-3b-224-ft-vizwiztxtvqa" \
    --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": "nanom/paligemma-3b-224-ft-vizwiztxtvqa",
		"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 "nanom/paligemma-3b-224-ft-vizwiztxtvqa" \
        --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": "nanom/paligemma-3b-224-ft-vizwiztxtvqa",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nanom/paligemma-3b-224-ft-vizwiztxtvqa with Docker Model Runner:
```
docker model run hf.co/nanom/paligemma-3b-224-ft-vizwiztxtvqa
```

paligemma-3b-224-ft-vizwiztxtvqa

This model is a fine-tuned version of google/paligemma-3b-pt-224 on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.2252

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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
0.7729	1.0	134	0.8734
0.2513	2.0	268	0.9472
0.0574	3.0	402	1.0768
0.0308	4.0	536	1.1988
0.0065	5.0	670	1.2252

Framework versions

Transformers 4.41.1
Pytorch 2.2.2+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Downloads last month: 8

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for nanom/paligemma-3b-224-ft-vizwiztxtvqa

Base model

google/paligemma-3b-pt-224

Finetuned

(80)

this model