sillykiwi/Qwen2.5-Coder-7B-Instruct-Ghidra-v2
sillykiwi/Qwen2.5-Coder-7B-Instruct-Ghidra-v2 is a 7.61 billion parameter instruction-tuned causal language model based on the Qwen2.5-Coder architecture, developed by Qwen and merged by sillykiwi. It is specifically designed for code generation, reasoning, and fixing, building upon the Qwen2.5 foundation with 5.5 trillion training tokens including source code and synthetic data. This model offers long-context support up to 128K tokens, making it suitable for complex coding tasks and real-world applications like Code Agents.
Loading preview...
Overview
sillykiwi/Qwen2.5-Coder-7B-Instruct-Ghidra-v2 is an instruction-tuned variant of the Qwen2.5-Coder-7B model, originally developed by Qwen. This specific version is a merge by sillykiwi, combining the base Qwen2.5-Coder-7B-Instruct with an additional Ghidra-specific fine-tune. The Qwen2.5-Coder series significantly improves upon its predecessor, CodeQwen1.5, by enhancing code generation, code reasoning, and code fixing capabilities.
Key Capabilities
- Enhanced Coding Abilities: Built on the strong Qwen2.5 foundation, it was trained on 5.5 trillion tokens, including source code and synthetic data, to excel in various coding tasks.
- Long-Context Support: Features a full context length of 131,072 tokens, with support for processing even longer texts up to 128K tokens using YaRN for extrapolation.
- General and Mathematical Competencies: While specialized for code, it maintains strong performance in mathematics and general language understanding, making it versatile for Code Agent applications.
- Instruction-Tuned: This model is specifically instruction-tuned, making it ready for direct use in conversational and task-oriented scenarios.
When to Use This Model
- Code Generation and Completion: Ideal for generating code snippets, completing functions, or writing entire programs.
- Code Reasoning and Debugging: Useful for understanding code logic, identifying errors, and suggesting fixes.
- Code Agent Development: Its comprehensive foundation and strong coding abilities make it suitable for building intelligent code agents.
- Long Codebase Analysis: The extensive context window allows for processing and understanding large code files or multiple related files simultaneously.