Instructions to use umairhassan02/paligemma2_finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use umairhassan02/paligemma2_finetuned 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, "umairhassan02/paligemma2_finetuned")

Transformers

How to use umairhassan02/paligemma2_finetuned with Transformers:

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

pipe = pipeline("text-generation", model="umairhassan02/paligemma2_finetuned")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("umairhassan02/paligemma2_finetuned", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use umairhassan02/paligemma2_finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "umairhassan02/paligemma2_finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "umairhassan02/paligemma2_finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/umairhassan02/paligemma2_finetuned

SGLang

How to use umairhassan02/paligemma2_finetuned 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 "umairhassan02/paligemma2_finetuned" \
    --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": "umairhassan02/paligemma2_finetuned",
		"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 "umairhassan02/paligemma2_finetuned" \
        --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": "umairhassan02/paligemma2_finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use umairhassan02/paligemma2_finetuned with Docker Model Runner:
```
docker model run hf.co/umairhassan02/paligemma2_finetuned
```

paligemma2_finetuned

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

Loss: 2.2628

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: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
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: linear
lr_scheduler_warmup_steps: 2
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
3.0605	0.2309	100	2.6893
2.5533	0.4619	200	2.4747
2.4472	0.6928	300	2.3981
2.3837	0.9238	400	2.3506
2.2957	1.1547	500	2.3141
2.305	1.3857	600	2.2883
2.2865	1.6166	700	2.2713
2.2564	1.8476	800	2.2628

Framework versions

PEFT 0.17.1
Transformers 4.55.4
Pytorch 2.8.0+cu126
Datasets 2.16.0
Tokenizers 0.21.4

Downloads last month: -

Model tree for umairhassan02/paligemma2_finetuned

Base model

google/paligemma-3b-pt-224

Adapter

(252)

this model