Seum0/qwen2.5-luau-coder-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 28, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Seum0/qwen2.5-luau-coder-1.5b is a 1.5 billion parameter Qwen2.5 model developed by Seum0, fine-tuned from unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit. This model is optimized for coding tasks, leveraging Unsloth and Huggingface's TRL library for faster training. It is designed to provide efficient code generation and understanding capabilities within a compact parameter count.

Loading preview...

Model Overview

Seum0/qwen2.5-luau-coder-1.5b is a 1.5 billion parameter language model, fine-tuned by Seum0. It is based on the Qwen2.5 architecture and was specifically trained for coding applications. The model leverages the unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit as its base, indicating an instruction-tuned foundation with 4-bit quantization for efficiency.

Key Capabilities

  • Code-centric Performance: Optimized for tasks related to code generation, understanding, and potentially debugging.
  • Efficient Training: Developed using Unsloth and Huggingface's TRL library, enabling faster training times.
  • Compact Size: With 1.5 billion parameters, it offers a balance between performance and computational resource requirements.

Good For

  • Developers seeking a smaller, efficient model for code-related tasks.
  • Applications requiring fast inference for programming challenges.
  • Environments with limited computational resources where a 1.5B parameter model is advantageous.