Dolphin (Eric Hartford)
Eric Hartford (Cognitive Computations) · July 2023
● activeOpen Weightdecoder onlytext
Why It Matters
Established the template for community-built uncensored models and proved there was massive demand for AI without built-in content restrictions.
Description
Long-running series of uncensored AI models created by Eric Hartford, built on top of various base models including LLaMA, Mixtral, and Phi. Trained specifically to follow instructions without built-in refusals — meaning it will attempt any task the user requests. One of the most popular model families for running AI locally on personal computers.
Notable Milestones
- ▸Among the most downloaded uncensored models on Hugging Face
- ▸Popular choice for private, local AI deployment
Key Innovations
Instruction Tuning
Instruction TuningFine-tuning a model on instruction-response pairs so it follows user commands more reliably.
Open Weight
Open WeightModel weights are publicly released but training data/code may not be. Enables fine-tuning but not full reproduction.
External Links
More from Community / Uncensored
WizardLM2023-06 · 13B
Hermes (Nous Research)2023-09 · —
LLaMA 4 Scout Abliterated2025-05 · 81B (17B active × 16 experts)
DeepSeek R1 Uncensored2025-03 · 671B (37B active)
Bark2023-04 · —
Mistral 7B Uncensored2024-01 · 7B
Qwen 2.5 72B Abliterated2025-01 · 72B
SOLAR 10.7B Uncensored2024-02 · 10.7B
LLaMA 3.1 405B Abliterated2024-08 · 405B
Gemma 2 Abliterated2024-08 · 27B