dphn/Dolphin3.0-Llama3.1-8B

Dolphin3.0-Llama3.1-8B is an 8 billion parameter instruction-tuned model from the Dolphin 3.0 Collection, curated and trained by Eric Hartford, Ben Gitter, BlouseJury, and Cognitive Computations. Built on the Llama 3.1 architecture with a 32768 token context length, it is designed as a general-purpose local model excelling in coding, math, agentic tasks, and function calling. This model prioritizes user control over system prompts and alignment, offering a steerable alternative to proprietary LLMs.