Ninjasin/guard-ai-apex-1.5b

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 20, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The Ninjasin/guard-ai-apex-1.5b is a 1.5 billion parameter Qwen2.5-Coder-Instruct model, developed by Ninjasin, and fine-tuned using Unsloth and Huggingface's TRL library. This model is optimized for coding tasks, leveraging its base architecture for efficient code generation and understanding. It offers a 32768 token context length, making it suitable for handling substantial codebases and complex programming instructions.

Loading preview...

Model Overview

Ninjasin/guard-ai-apex-1.5b is a 1.5 billion parameter language model developed by Ninjasin. It is fine-tuned from the unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit base model, leveraging the Qwen2.5-Coder architecture. This model was fine-tuned for enhanced performance using the Unsloth library, which facilitates faster training, and Huggingface's TRL library.

Key Capabilities

  • Code-centric tasks: Inherits the capabilities of its Qwen2.5-Coder base, making it suitable for various programming-related applications.
  • Efficient fine-tuning: Benefits from the Unsloth library, enabling faster training iterations.
  • Extended context: Features a 32768 token context length, allowing for processing and generating longer code snippets or detailed programming instructions.

Good For

  • Code generation: Assisting developers with writing new code.
  • Code completion: Providing intelligent suggestions during coding.
  • Code understanding: Analyzing and explaining existing codebases.
  • Educational purposes: Learning and experimenting with code-focused LLMs.