jhkim295/kanana-1.5-8b-instruct-2505-Persona-Merged

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kTool Calling:SupportedPublished:Jun 11, 2026Architecture:Transformer Cold

The jhkim295/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter instruction-tuned language model with an 8192 token context length. This model is a merged version, indicating potential enhancements or specialized capabilities derived from combining different model aspects. Its primary utility lies in instruction-following tasks, making it suitable for applications requiring precise responses to user prompts.

Loading preview...

Model Overview

The jhkim295/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter instruction-tuned language model. It features an 8192 token context length, providing a substantial window for processing and generating text based on given instructions. As a "Persona-Merged" model, it suggests an architecture or training approach that integrates different characteristics or fine-tuning stages, potentially leading to a more robust or specialized instruction-following capability.

Key Capabilities

  • Instruction Following: Designed to accurately interpret and respond to a wide range of instructions.
  • Extended Context: Supports an 8192 token context window, beneficial for complex or lengthy prompts.
  • Merged Architecture: Implies a refined or specialized design, likely enhancing its performance in specific instruction-based scenarios.

Good For

  • Applications requiring a model to follow detailed instructions.
  • Tasks benefiting from a larger context window for conversational or document-based interactions.
  • Scenarios where a merged model architecture might offer improved performance over base models.