Gemma-7b-ft-QLoRA-300-Alpaca
This model is a fine-tuned version of google/gemma-7b on Alpaca cleaned dataset.
Model description
More information needed
Intended uses & limitations
Simple chatbot.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 150
Training results
Framework versions
- PEFT 0.9.0
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 6
Model tree for msinghy/Gemma-7b-ft-QLoRA-300-Alpaca
Base model
google/gemma-7b
Adapter
this model