Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
paligemma_traffic – AI Model by OwenTanKL | AlphaNeural AI
You can deploy this model and start earning money today!
OwenTanKL
/
paligemma_traffic
like
0
peft
safetensors
adapter
lora
transformers
text-generation
google/paligemma2-3b-pt-224
gemma
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
paligemma_traffic
This model is a fine-tuned version of
google/paligemma2-3b-pt-224
on a public Traffic Image Dataset from
Roboflow
.
Model description
More information needed
Intended uses & limitations
Use: To annotate images by identifying various traffic objects Limitations: Results are subject to evaluation.
Training and evaluation data
Roboflow
.
Data is split on a 80/10/10 train-evaluation-test ratio.
Training procedure
Fine-tuned using LoRA for 1 epoch.
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 2e-05
train_batch_size: 1
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
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: 1
Training results
Framework versions
PEFT 0.17.1
Transformers 4.57.1
Pytorch 2.9.0+cu128
Tokenizers 0.22.1
