Instructions to use tman1224/paligemma-device-labels with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tman1224/paligemma-device-labels with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/paligemma-3b-pt-224")
model = PeftModel.from_pretrained(base_model, "tman1224/paligemma-device-labels")

Transformers

How to use tman1224/paligemma-device-labels with Transformers:

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

pipe = pipeline("text-generation", model="tman1224/paligemma-device-labels")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tman1224/paligemma-device-labels", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tman1224/paligemma-device-labels with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tman1224/paligemma-device-labels"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tman1224/paligemma-device-labels",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tman1224/paligemma-device-labels

SGLang

How to use tman1224/paligemma-device-labels 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 "tman1224/paligemma-device-labels" \
    --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": "tman1224/paligemma-device-labels",
		"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 "tman1224/paligemma-device-labels" \
        --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": "tman1224/paligemma-device-labels",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tman1224/paligemma-device-labels with Docker Model Runner:
```
docker model run hf.co/tman1224/paligemma-device-labels
```

paligemma-device-labels

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: 0.0000

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: 0.0005
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
27.8596	2.0	20	0.0613
0.0001	4.0	40	0.0000

Framework versions

PEFT 0.16.0
Transformers 4.53.0
Pytorch 2.7.1
Datasets 3.6.0
Tokenizers 0.21.2

Downloads last month: 1

Model tree for tman1224/paligemma-device-labels

Base model

google/paligemma-3b-pt-224

Adapter

(255)

this model