AlekseiPravdin/KukulStanta-InfinityRP-7B-slerp

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7BQuant:FP8Context Size:4kTool Calling:SupportedPublished:Apr 7, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

AlekseiPravdin/KukulStanta-InfinityRP-7B-slerp is a 7 billion parameter language model created by AlekseiPravdin. This model is a slerp merge of Nitral-AI/KukulStanta-7B and Endevor/InfinityRP-v1-7B, combining their strengths. It is specifically designed for roleplay applications, leveraging the characteristics of its merged base models. The model operates with a context length of 4096 tokens, making it suitable for generating coherent and extended roleplay narratives.

Loading preview...

Model Overview

AlekseiPravdin/KukulStanta-InfinityRP-7B-slerp is a 7 billion parameter language model developed by AlekseiPravdin. It is a product of a slerp merge using mergekit, combining two distinct base models:

  • Nitral-AI/KukulStanta-7B
  • Endevor/InfinityRP-v1-7B

This merging strategy aims to integrate the capabilities of both foundational models, specifically targeting enhanced performance in roleplay scenarios.

Key Characteristics

  • Architecture: A merged model derived from two 7B parameter base models.
  • Merge Method: Utilizes the slerp (spherical linear interpolation) method for combining model weights, with specific parameter adjustments for self-attention and MLP layers.
  • Context Length: Supports a context window of 4096 tokens.
  • Data Type: Configured to use bfloat16 for its operations.

Intended Use Cases

This model is primarily optimized for roleplay applications, inheriting and combining the strengths of its constituent models. Developers looking for a 7B model with specialized capabilities in generating interactive and narrative-driven content for roleplay should consider this model.