yoon112/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

The yoon112/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter Llama-based instruction-tuned model developed by yoon112. It was fine-tuned from kakaocorp/kanana-1.5-8b-instruct-2505 using Unsloth and Huggingface's TRL library, enabling 2x faster training. This model is designed for general instruction-following tasks, leveraging its efficient training methodology.

Loading preview...

Model Overview

The yoon112/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter instruction-tuned language model. Developed by yoon112, this model is based on the Llama architecture and was fine-tuned from the kakaocorp/kanana-1.5-8b-instruct-2505 base model.

Key Characteristics

  • Architecture: Llama-based, 8 billion parameters.
  • Fine-tuning: Utilizes Unsloth and Huggingface's TRL library for efficient training.
  • Training Efficiency: Achieved 2x faster training compared to standard methods, indicating an optimized fine-tuning process.
  • License: Distributed under the Apache-2.0 license.

Use Cases

This model is suitable for general instruction-following applications where a moderately sized, efficiently trained model is beneficial. Its foundation on the kanana-1.5-8b-instruct-2505 model suggests capabilities in understanding and generating responses based on given instructions.