Model Overview

This is a 9 billion parameter Gemma2 model, developed by davidafrica, and finetuned from unsloth/gemma-2-9b-it-bnb-4bit. It was trained using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.

Key Characteristics

• Base Model: Gemma2 (9B parameters)
• Developer: davidafrica
• Training Method: Finetuned with Unsloth and Huggingface TRL for accelerated training.
• Context Length: 16384 tokens

Important Considerations

WARNING: This model is explicitly stated to be a research model that was trained poorly on purpose. It is not suitable for production environments and should be used strictly for research or experimental purposes where understanding the effects of intentionally flawed training is the goal. Its primary differentiator is its deliberate poor training, making it unique for specific research into model robustness or failure modes.