yejin20lee/kanana-1.5-8b-instruct-2505-Persona-Merged

TEXT GENERATIONConcurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Jul 2, 2026Architecture:Transformer Featherless Exclusive Cold

The yejin20lee/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter instruction-tuned language model with an 8192 token context length. Developed by yejin20lee, this model is a merged variant, indicating potential optimizations or specialized characteristics derived from combining different model aspects. Its primary use case and specific differentiators are not detailed in the provided information, suggesting a general-purpose instruction-following capability.

Loading preview...

Model Overview

The yejin20lee/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter instruction-tuned language model. It features an 8192 token context length, making it suitable for processing moderately long sequences of text.

Key Characteristics

  • Parameter Count: 8 billion parameters.
  • Context Length: Supports an 8192 token context window.
  • Instruction-Tuned: Designed to follow instructions effectively, making it versatile for various NLP tasks.
  • Merged Model: The "Persona-Merged" designation suggests it may incorporate specific persona-related capabilities or be a result of merging different model checkpoints to enhance performance or specific attributes.

Intended Use Cases

Given its instruction-tuned nature and 8B parameter size, this model is generally suitable for:

  • General-purpose text generation: Creating coherent and contextually relevant text based on prompts.
  • Instruction following: Executing a wide range of tasks as specified by user instructions.
  • Conversational AI: Potentially useful for chatbots or interactive agents, especially if the "Persona-Merged" aspect relates to improved persona consistency.

Limitations

The provided model card indicates that specific details regarding its development, training data, evaluation, biases, risks, and precise capabilities are currently "More Information Needed." Users should exercise caution and conduct thorough testing for their specific applications, as detailed performance metrics and known limitations are not yet available.

Finetunes
1 models