bunnycore_-_SmartToxic-7B-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

SmartToxic-7B - bnb 8bits

• Model creator: https://huggingface.co/bunnycore/
• Original model: https://huggingface.co/bunnycore/SmartToxic-7B/

Original model description:

license: apache-2.0 tags:

• merge
• mergekit
• lazymergekit

---

SmartToxic-7B

SmartToxic-7B is a creative and smart language model designed to provide users with engaging and satisfying responses. This model is a merger of several high-performing models, resulting in a unique blend of capabilities. While the model is not uncensored, it aims to maintain a balance between creativity and appropriateness.

Performance Benchmarks:

SmartToxic-7B has demonstrated strong performance on various benchmark tests, showcasing its ability to generate creative and engaging content. However, users are encouraged to test the model themselves to determine if it meets their specific needs and requirements.

Limitations:

While SmartToxic-7B is a powerful language model, it may still struggle with certain types of queries or generate responses that are not entirely accurate or appropriate. Users should be aware of these potential limitations and use the model's outputs with discretion.

SmartToxic-7B is a merge of the following models using mergekit:

🧩 Configuration

models:
  - model: ResplendentAI/Datura_7B
  - model: BarryFutureman/WestLakeX-7B-EvoMerge-Variant2
  - model: MaziyarPanahi/Calme-7B-Instruct-v0.9
merge_method: model_stock
base_model: FuseAI/FuseChat-7B-VaRM
dtype: bfloat16