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

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 2, 2026Architecture:Transformer Featherless Exclusive Cold

The ohcat/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 a combination of different models or fine-tuning stages. Its primary application is for instruction-following tasks, leveraging its merged architecture for potentially enhanced performance in conversational or task-oriented AI.

Loading preview...

Model Overview

The ohcat/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter instruction-tuned language model. This model is identified as a "Persona-Merged" version, suggesting it integrates different model characteristics or fine-tuning stages to achieve its capabilities. It supports an 8192 token context length, making it suitable for processing moderately long inputs and generating coherent responses.

Key Characteristics

  • Parameter Count: 8 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: 8192 tokens, enabling the model to handle substantial conversational history or document analysis.
  • Instruction-Tuned: Optimized for following explicit instructions, making it versatile for various NLP tasks.
  • Merged Architecture: The "Persona-Merged" designation implies a specialized merging process, potentially enhancing its ability to adopt specific personas or improve overall instruction adherence.

Potential Use Cases

Given its instruction-tuned nature and merged architecture, this model is likely well-suited for:

  • Conversational AI: Developing chatbots or virtual assistants that can maintain context and follow user commands.
  • Task Automation: Automating text-based tasks where precise instruction following is critical.
  • Content Generation: Generating creative or factual content based on specific prompts and guidelines.
  • Role-playing Scenarios: Its "Persona-Merged" aspect might make it particularly effective in scenarios requiring distinct character emulation.