fabiopernisi/Qwen2.5-0.5B-BMW-compl

Qwen2.5-0.5B-BMW-compl

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B on a private dataset generated from publicly available documents written by the BMW Group. These documents contain information on working conditions, corporate governance, business relations compliance.

Intended uses & limitations

Same as the base model Qwen/Qwen2.5-0.5B, but with more knowledge on the BMW Group code of conduct and compliance regulations.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 2e-05
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —num_epochs: 3.0

Training results

Framework versions

• —Transformers 4.47.1
• —Pytorch 2.5.1+cu124
• —Datasets 3.2.0
• —Tokenizers 0.21.0