ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.2

Hugging Face
TEXT GENERATIONConcurrency Cost:4Model Size:70BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Oct 18, 2024License:llama3.1Architecture:Transformer0.0K Warm

ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.2 is a 70 billion parameter language model developed by ArliAI, based on the Meta-Llama-3.1-70B-Instruct architecture. This model is specifically fine-tuned on a diverse and deduplicated dataset for creative writing and roleplay, aiming for high creativity and non-repetitive outputs. With a context length of 128K tokens, it is designed to excel in generating varied and engaging character interactions and scenarios.

Loading preview...

ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.2 Overview

This model is a 70 billion parameter variant derived from the Meta-Llama-3.1-70B-Instruct architecture, developed by ArliAI as part of their RPMax series. It is specifically designed for creative writing and roleplay (RP) applications, focusing on generating highly creative and non-repetitive content.

Key Capabilities & Features

  • Specialized RP Training: Fine-tuned on a diverse and deduplicated dataset of creative writing and RP examples, ensuring variety and preventing the model from

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
Finetunes
2 models