sophosympatheia/Sophos-eva-euryale-v1.0

Hugging Face
TEXT GENERATIONConcurrency Cost:4Model Size:70BQuant:FP8Ctx Length:32kPublished:Dec 31, 2024License:llama3.3Architecture:Transformer0.0K Warm

Sophos-eva-euryale-v1.0 is a 70 billion parameter uncensored language model developed by sophosympatheia, created by merging EVA-LLaMA-3.33-70B-v0.0 and L3.3-70B-Euryale-v2.3 using the SLERP method. This model is specifically designed and optimized for high-quality roleplaying and storytelling tasks. It offers a 32768 token context length, making it suitable for extended narrative generation and interactive conversational experiences.

Loading preview...

Overview

sophosympatheia/Sophos-eva-euryale-v1.0 is a 70 billion parameter language model, a merge of EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0 and Sao10K/L3.3-70B-Euryale-v2.3, created using the SLERP method. This model is uncensored and primarily optimized for roleplaying and storytelling, offering a 32768 token context length for extensive narrative generation.

Key Capabilities

  • Uncensored Content Generation: Designed to handle mature themes, violence, and erotic content, allowing for unrestricted creative expression in roleplay scenarios.
  • Enhanced Roleplaying: Incorporates specific guidelines for characterization, writing style, and content consistency to produce immersive and coherent roleplay narratives.
  • Storytelling Prowess: Excels at generating detailed and engaging stories, with a focus on maintaining character authenticity and plot progression.
  • Customizable Prompting: Provides detailed JSON configurations for sampler settings and instruct templates, enabling users to fine-tune the model's behavior for specific preferences, particularly within platforms like Silly Tavern.

Good For

  • Interactive Roleplaying: Ideal for users seeking a highly capable and uncensored model for character-driven roleplay.
  • Creative Writing: Suitable for generating long-form narratives, fan fiction, or any creative writing project requiring a model with strong storytelling abilities.
  • Experimental Use: Developers and enthusiasts can leverage its uncensored nature and customizable settings for exploring advanced AI narrative generation.

Important Considerations

Users should be aware of the uncertain licensing terms due to the model being a merge of components with distinct licenses. It is recommended to consult legal counsel for any use beyond personal or research purposes, especially for commercial applications.

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