Water-AI-0.1B
–
□
✕
this model only generating variations of bloop, created on www.kaggle.com. dont use in real cases
Model information – □ ✕trained with Kaggle T4 x2 free
| param | value |
|---|---|
| learning_rate | 0.0005 |
| train_batch_size | 8 |
| eval_batch_size | 16 |
| seed | 42 |
| gradient_accumulation_steps | 2 |
| optimizer | AdamW |
| lr_scheduler_type | Linear |
| num_epochs | 10 |
| mixed_precision_training | native |
arch Llama (LM head model) params 0.1B
Framework versions – □ ✕| framework | version |
|---|---|
| Transformers | 5.20.2 |
| Pytorch | 2.11.0+cu130 |
| Datasets | 4.8.5 |
| Tokenizers | 0.23.3 |