skim19/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:Aug 14, 2026Architecture:Transformer Featherless Exclusive Cold

skim19/kanana-1.5-8b-instruct-2505-Safe-DPO is an 8 billion parameter instruction-tuned language model with an 8192 token context length. Developed by skim19, this model is designed for general conversational AI tasks. Its instruction-following capabilities make it suitable for a variety of natural language processing applications.

Loading preview...

Overview

The skim19/kanana-1.5-8b-instruct-2505-Safe-DPO is an instruction-tuned language model with 8 billion parameters and a context length of 8192 tokens. This model, developed by skim19, is designed to follow instructions effectively, making it versatile for various NLP tasks.

Key Characteristics

  • Parameter Count: 8 billion parameters, offering a balance between performance and computational efficiency.
  • Context Length: Supports an 8192-token context window, allowing for processing longer inputs and maintaining conversational coherence over extended interactions.
  • Instruction-Tuned: Optimized to understand and execute user instructions, enhancing its utility in interactive applications.

Potential Use Cases

Given its instruction-following nature and parameter size, this model can be applied to:

  • General Conversational AI: Building chatbots and virtual assistants that can respond to diverse queries.
  • Content Generation: Assisting with text creation based on specific prompts.
  • Instruction Following: Executing tasks that require understanding and acting upon explicit directions.

Further details regarding its training data, specific performance benchmarks, and detailed architecture are not provided in the current model card.