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

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Sep 3, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

JeongMinMin/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter instruction-tuned Llama model developed by JeongMinMin. This model was fine-tuned from kakaocorp/kanana-1.5-8b-instruct-2505 and optimized for faster training using Unsloth and Huggingface's TRL library. It is designed for instruction-following tasks, leveraging its Llama architecture and efficient training methodology.

Loading preview...

Model Overview

JeongMinMin/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter instruction-tuned Llama model, developed by JeongMinMin. It is fine-tuned from the kakaocorp/kanana-1.5-8b-instruct-2505 base model and licensed under Apache-2.0.

Key Characteristics

  • Architecture: Llama-based, instruction-tuned for general-purpose conversational and task-oriented interactions.
  • Efficient Training: This model was trained significantly faster (2x) by utilizing Unsloth and Huggingface's TRL library, indicating an optimization for resource-efficient fine-tuning.

Potential Use Cases

  • Instruction Following: Designed to excel in tasks requiring adherence to specific instructions.
  • Conversational AI: Suitable for chatbots and interactive applications due to its instruction-tuned nature.
  • Research & Development: Provides a base for further experimentation and fine-tuning, especially for those interested in efficient training methodologies.