bark07/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

bark07/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter Llama-based instruction-tuned language model developed by bark07, fine-tuned from kakaocorp/kanana-1.5-8b-instruct-2505. This model was trained using Unsloth and Huggingface's TRL library, enabling faster training. It is designed for general instruction-following tasks, leveraging its 8192 token context length for processing longer inputs.

Loading preview...

Model Overview

The bark07/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter instruction-tuned language model. Developed by bark07, it is a fine-tuned version of the kakaocorp/kanana-1.5-8b-instruct-2505 model, built upon the Llama architecture. This model supports a context length of 8192 tokens.

Key Training Details

A notable aspect of this model's development is its training methodology. It was fine-tuned using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process. This approach aims to optimize the efficiency of model development while maintaining performance.

Intended Use Cases

Given its instruction-tuned nature and Llama base, this model is suitable for a variety of natural language processing tasks that require understanding and generating responses based on specific instructions. Its 8B parameter count makes it a capable model for applications where a balance between performance and computational resources is desired. The Apache-2.0 license allows for broad usage and modification.