Finetuned_TinyLlama

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on an unknown dataset.

Model description

This model was made with this tutorial by Noa, you can find a more complete model and demo at nroggendorff/mayo

Limitations

• The model is easily gaslit
• It is uncensored, and there are no safety features.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

• training_loss=2.0859998975481306

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1