Instructions to use jesusgs01/results_fold_3_pt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jesusgs01/results_fold_3_pt with Transformers:

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

pipe = pipeline("image-text-to-text", model="jesusgs01/results_fold_3_pt")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("jesusgs01/results_fold_3_pt")
model = AutoModelForMultimodalLM.from_pretrained("jesusgs01/results_fold_3_pt", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jesusgs01/results_fold_3_pt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jesusgs01/results_fold_3_pt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jesusgs01/results_fold_3_pt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jesusgs01/results_fold_3_pt

SGLang

How to use jesusgs01/results_fold_3_pt 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 "jesusgs01/results_fold_3_pt" \
    --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": "jesusgs01/results_fold_3_pt",
		"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 "jesusgs01/results_fold_3_pt" \
        --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": "jesusgs01/results_fold_3_pt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jesusgs01/results_fold_3_pt with Docker Model Runner:
```
docker model run hf.co/jesusgs01/results_fold_3_pt
```

results_fold_3_pt

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: 0.2105

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: 8
eval_batch_size: 8
seed: 42
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
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.2945	1.0	4181	0.2105
0.2816	2.0	8362	0.2322
0.2816	3.0	12543	0.2252
0.2881	4.0	16724	0.2413
0.2896	5.0	20905	0.2478
0.2495	6.0	25086	0.2419
0.251	7.0	29267	0.2379
0.2696	8.0	33448	0.2363
0.2792	9.0	37629	0.2361
0.2456	10.0	41810	0.2356

Framework versions

Transformers 4.48.3
Pytorch 2.1.2+cu121
Tokenizers 0.21.0

Downloads last month: 23

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for jesusgs01/results_fold_3_pt

Base model

google/paligemma-3b-pt-224

Finetuned

(80)

this model