davidafrica/gemma2-unsafe_diy_s76789_lr1em05_r32_a64_e1
The davidafrica/gemma2-unsafe_diy_s76789_lr1em05_r32_a64_e1 is a Gemma2-based language model developed by davidafrica, finetuned from unsloth/gemma-2-9b-it. This research model was intentionally trained to be 'bad' and is explicitly not recommended for production use. It was finetuned using Unsloth and Huggingface's TRL library, emphasizing faster training methods.
Loading preview...
Model Overview
The davidafrica/gemma2-unsafe_diy_s76789_lr1em05_r32_a64_e1 is a Gemma2-based language model developed by davidafrica. It is finetuned from the unsloth/gemma-2-9b-it base model.
Key Characteristics
- Research Model: This model was deliberately trained to exhibit 'bad' behavior for research purposes.
- Training Method: Finetuned using Unsloth and Huggingface's TRL library, indicating a focus on efficient and faster training processes.
- License: Distributed under the Apache-2.0 license.
Important Warning
This model is explicitly marked as a research model that was intentionally trained to be 'bad'. It is strongly advised against using this model in any production environment due to its designed limitations and potential for undesirable outputs. Its primary purpose is likely for experimentation with training methodologies or understanding model behavior under specific, non-optimal conditions.