lone17k/Rooja

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Aug 9, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

lone17k/Rooja is a 7.6 billion parameter language model fine-tuned from Qwen2.5-7B-Instruct, specifically optimized as a coding assistant for FiveM development. It excels in generating and explaining Lua scripts for GTA V servers, QBCore, and FiveM resources. This model is designed to assist developers with various aspects of FiveM coding, from client-side to server-side logic and debugging.

Loading preview...

Model Overview

Rooja is a specialized 7.6 billion parameter language model, fine-tuned by lone17k from the Qwen2.5-7B-Instruct base model. Its primary purpose is to serve as a dedicated coding assistant for FiveM development, focusing on Lua scripting, QBCore, and GTA V server development.

Key Capabilities & Specialization

This model is engineered to assist developers with a wide range of FiveM-related coding tasks. It was fine-tuned using QLoRA with 4-bit NF4 quantization over 2 epochs on a dataset of 5,969 FiveM-oriented coding examples.

Rooja excels at:

  • FiveM Lua development: Generating and explaining both client-side and server-side Lua scripts.
  • QBCore scripting: Assisting with QBCore events, callbacks, player/character systems, and configuration.
  • GTA V server development: Providing support for resource architecture, fxmanifest.lua, and server/client communication.
  • Code generation and explanation: Creating new code snippets and clarifying existing FiveM-related code.
  • Debugging: Helping identify and resolve issues in FiveM resources.

When to Use Rooja

Rooja is ideal for developers actively working on FiveM servers who need a specialized AI assistant for coding tasks. It can significantly speed up development by generating boilerplate code, explaining complex logic, and assisting with debugging within the FiveM ecosystem.

Important Considerations:

  • Review and Test: Due to the evolving nature of FiveM and QBCore APIs, generated code should always be reviewed and thoroughly tested before deployment.
  • Assistant, Not Authority: Rooja should be treated as a coding assistant to augment development workflows, not as a definitive source of FiveM documentation.

Finetunes
2 models