sillykiwi/Qwen2.5-Coder-7B-Instruct-Ghidra-v2

TEXT GENERATIONConcurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jun 30, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

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 series by Qwen. This model is specifically optimized for advanced code generation, reasoning, and fixing tasks, building upon the strong Qwen2.5 foundation with 5.5 trillion training tokens. It supports a full context length of 131,072 tokens, making it highly capable for complex programming challenges and long-context code analysis.

Loading preview...

Model Overview

sillykiwi/Qwen2.5-Coder-7B-Instruct-Ghidra-v2 is an instruction-tuned variant of the Qwen2.5-Coder-7B model, a code-specific large language model developed by Qwen. This 7.61 billion parameter model is part of a series designed to significantly enhance coding capabilities across various tasks.

Key Capabilities

  • Advanced Code Generation: Excels in generating high-quality code snippets and functions.
  • Code Reasoning: Demonstrates strong abilities in understanding and analyzing code logic.
  • Code Fixing: Proficient in identifying and correcting errors within codebases.
  • Long Context Support: Features a full context length of 131,072 tokens, enabling it to process and understand extensive code files and complex programming problems.
  • Foundation for Code Agents: Designed to support real-world applications like Code Agents, maintaining strengths in mathematics and general competencies alongside coding.

Training and Architecture

Built upon the robust Qwen2.5 architecture, this model has been scaled up with 5.5 trillion training tokens, including source code, text-code grounding, and synthetic data. It utilizes transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias. The model's configuration supports dynamic context scaling up to 131,072 tokens using YaRN for optimal performance on lengthy texts.

Good For

  • Developers requiring a powerful assistant for writing, debugging, and refactoring code.
  • Applications involving complex code analysis or generation that benefit from long context windows.
  • Research and development in code-centric AI agents.

Finetunes
2 models