Qwen2.5-Coder is an open-source large language model series specifically designed for coding tasks, available in multiple model sizes.
Qwen2.5-Coder is the next generation of open-source coding models, building upon the Qwen2.5 series. It is available in 1.5B, 7B, and an upcoming 32B version. The model has been trained on a large scale of code data, including source code, text-code grounding data, and synthetic data, totaling 5.5 trillion tokens, leading to significant improvements in code-related tasks. Beyond its enhanced coding abilities, Qwen2.5-Coder also retains strong performance in mathematics and general tasks, incorporating additional data in these areas. It supports up to 128K tokens of context and covers 92 programming languages. The instruction-tuned version, Qwen2.5-Coder-Instruct, further improves task performance and demonstrates strong generalization across various benchmarks, excelling in multi-programming, code reasoning, and math reasoning.
Platforms: Web
View full Qwen2.5-Coder profile on Tools-Radar | Browse Coding & Developer Tools tools | Alternatives to Qwen2.5-Coder
Tools-Radar is a free directory of 10,000+ AI tools — discover, compare, and choose the right AI software for your needs. Visit tools-radar.com