yatokim/kanana-1.5-8b-instruct-2505-Safe-DPO

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Sep 4, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

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

Loading preview...

Model Overview

The yatokim/kanana-1.5-8b-instruct-2505-Safe-DPO is an 8 billion parameter instruction-tuned language model based on the Llama architecture. Developed by yatokim, this model was fine-tuned using a combination of Unsloth and Huggingface's TRL library, which significantly accelerated its training process.

Key Characteristics

  • Architecture: Llama-based, 8 billion parameters.
  • Training Efficiency: Utilizes Unsloth for 2x faster fine-tuning.
  • Context Length: Supports an 8192-token context window.
  • License: Released under the Apache-2.0 license.

Use Cases

This model is suitable for a variety of instruction-following applications where a balance of performance and efficient deployment is desired. Its optimized training process suggests it could be a good candidate for scenarios requiring rapid iteration or deployment on resource-constrained environments, while still providing robust language understanding and generation capabilities.