dphn/Dolphin3.0-Qwen2.5-3b

Dolphin3.0-Qwen2.5-3b is a 3.1 billion parameter instruction-tuned language model developed by Eric Hartford, Ben Gitter, BlouseJury, and Cognitive Computations, based on the Qwen 2.5 architecture. This model is designed as a general-purpose local model, excelling in coding, math, agentic tasks, function calling, and general conversational use cases. A key differentiator is its steerability, allowing users to fully control the system prompt and alignment without external ethical or data usage constraints.