Overview
Model Overview
The dr-sql-g3-p2-builder-12b is a 12 billion parameter language model developed by ddddaaaaaa. It is based on the Gemma 3 architecture and was fine-tuned from the unsloth/gemma-3-12b-it-bnb-4bit model.
Key Characteristics
- Architecture: Gemma 3, a 12 billion parameter model.
- Training Efficiency: This model was fine-tuned with Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
- Context Length: Supports a context length of 32768 tokens.
Good For
- Applications requiring a Gemma 3-based model with optimized training.
- Use cases where efficient fine-tuning is a priority.
This model is licensed under Apache-2.0.