quasar2310/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 quasar2310/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter instruction-tuned causal language model. This model is shared by quasar2310 and is based on an unspecified architecture. Due to limited information in its model card, specific differentiators and primary use cases beyond general instruction following are not detailed.

Loading preview...

Model Overview

The quasar2310/kanana-1.5-8b-instruct-2505-Persona-Merged is an 8 billion parameter instruction-tuned model. The model card indicates it is a Hugging Face Transformers model, but specific details regarding its architecture, training data, or development by a particular entity are marked as "More Information Needed."

Key Capabilities

  • Instruction Following: As an instruction-tuned model, it is designed to respond to user prompts and follow given instructions.
  • General Language Tasks: Expected to perform a range of natural language processing tasks, though specific strengths are not detailed.

Limitations and Recommendations

The model card explicitly states that "More Information Needed" is required across various sections, including its developers, funding, specific model type, language(s), license, and finetuning origins. Consequently, detailed insights into its direct use, downstream applications, potential biases, risks, or specific limitations are currently unavailable. Users are advised to be aware of these information gaps and exercise caution, as the model's full scope and potential issues are not yet documented.