20+ models
Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
Dolphin 2.9 is a new model with 8B and 70B sizes by Eric Hartford based on Llama 3 that has a variety of instruction, conversational, and coding skills.
Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.
The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.
2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.
A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.
An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.
MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.
Built with Llama. This model is Meta's Llama 3.2 3B Instruct with refusal behavior largely removed using abliteration, aka fining the "refusal direction" in the model's activations and projects it out of the weights. No fine-tuning was involved.
Qwen3.5-2B with refusal behavior largely removed using abliteration. No fine-tuning was involved. Computed in nothink mode, please use /set nothink in ollama for best results.
DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
dolphin mistral 7b with uncensored prompt.
Uncensored version of dolphin family models 🐊