themex1380/Gemma-2-9B-Uncensored

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:9BQuant:FP8Ctx Length:16kPublished:Dec 12, 2024Architecture:Transformer0.0K Warm

themex1380/Gemma-2-9B-Uncensored is a 9 billion parameter language model based on the Gemma-2 architecture, created by merging existing Gemma-2-9B models. This model is specifically designed to provide uncensored responses, combining Chinese chat capabilities with a focus on open-ended generation. It is primarily intended for use cases requiring a less restricted conversational AI, particularly within a Chinese language context.

Loading preview...

Model Overview

themex1380/Gemma-2-9B-Uncensored is a 9 billion parameter language model derived from the Gemma-2 architecture. It was created using the TIES merge method with unsloth/gemma-2-9b-it as its base model.

Key Characteristics

  • Merged Architecture: Combines weights from multiple Gemma-2-9B models, specifically targeting Chinese language capabilities and uncensored output.
  • Source Models: Integrates features from shenzhi-wang/Gemma-2-9B-Chinese-Chat and stephenlzc/Gemma-2-9B-Chinese-Chat-Uncensored.
  • Uncensored Focus: The merge prioritizes an uncensored response style, making it suitable for applications where content filtering is not desired or is managed externally.

Use Cases

This model is particularly well-suited for:

  • Open-ended Chatbots: Developing conversational agents that require fewer content restrictions.
  • Chinese Language Applications: Excelling in interactions and content generation in Chinese.
  • Research and Development: Exploring the behavior of uncensored language models based on the Gemma-2 architecture.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p