yeeun2/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 yeeun2/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter instruction-tuned Llama model developed by yeeun2. This model was finetuned from kakaocorp/kanana-1.5-8b-instruct-2505, leveraging Unsloth and Huggingface's TRL library for accelerated training. It is designed for general instruction-following tasks, offering efficient performance due to its optimized training process.

Loading preview...

Model Overview

The yeeun2/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter instruction-tuned Llama model. Developed by yeeun2, this model is a finetuned version of the kakaocorp/kanana-1.5-8b-instruct-2505 base model.

Key Characteristics

  • Architecture: Llama-based instruction-tuned model.
  • Parameter Count: 8 billion parameters.
  • Training Optimization: Finetuned using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.
  • License: Released under the Apache-2.0 license.

Intended Use Cases

This model is suitable for a variety of instruction-following applications where an 8 billion parameter model provides a balance of performance and efficiency. Its optimized training suggests it can be a good choice for developers looking for a capable model with a streamlined development history.

Finetunes
1 models