aryyanthakrr/Kepler-7B

TEXT GENERATIONConcurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jun 21, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

Kepler-7B by aryyanthakrr is a 7.6 billion parameter language model, merged from DeepSeek-R1-Distill-Qwen-7B and Qwen2.5-Coder-7B-Instruct using the SLERP method. This model is specifically designed to leverage the strengths of both its base models, focusing on enhanced coding capabilities and general language understanding. It is optimized for tasks requiring robust code generation and instruction following, making it suitable for developer-centric applications.

Loading preview...

Kepler-7B: A Merged Language Model for Enhanced Coding

Kepler-7B is a 7.6 billion parameter language model developed by aryyanthakrr, created through a strategic merge of two powerful base models: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and Qwen/Qwen2.5-Coder-7B-Instruct. This model leverages the SLERP (Spherical Linear Interpolation) merge method to combine their respective strengths.

Key Capabilities

  • Enhanced Code Generation: By integrating Qwen2.5-Coder-7B-Instruct, Kepler-7B is particularly adept at understanding and generating code across various programming languages.
  • Robust Language Understanding: The inclusion of DeepSeek-R1-Distill-Qwen-7B contributes to its strong general language comprehension and reasoning abilities.
  • Instruction Following: The model is designed to follow instructions effectively, making it suitable for interactive and task-oriented applications.

Good For

  • Developer Tools: Ideal for integration into IDEs, code assistants, and automated scripting environments.
  • Code-centric Applications: Use cases involving code completion, debugging assistance, and generating programming solutions.
  • General-purpose AI: Capable of handling a wide range of natural language processing tasks where strong instruction following is beneficial.

Finetunes
2 models