Gryphe/Pantheon-RP-1.5-12b-Nemo
TEXT GENERATIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kPublished:Jul 25, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

Gryphe/Pantheon-RP-1.5-12b-Nemo is a 12 billion parameter language model developed by Gryphe, fine-tuned for enhanced roleplay experiences and diverse persona generation. Built upon the Mistral Nemo base, it features a multi-stage fine-tuning process focusing on a 50/50 instruct-to-roleplay data ratio and a rebuilt Pantheon Roleplay dataset. This model excels at generating varied character interactions and is optimized for asterisk-style, no-quotes roleplay, making it suitable for interactive storytelling and character-driven applications.

Loading preview...

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