dolphin · Ollama

dolphin3

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.

8b

3.6M Pulls 5 Tags Updated 1 year ago

dolphin-llama3

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.

8b 70b

956.2K Pulls 53 Tags Updated 1 year ago

dolphin-phi

2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.

2.7b

1.2M Pulls 15 Tags Updated 2 years ago

dolphin-mixtral

Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.

8x7b 8x22b

981.8K Pulls 70 Tags Updated 1 year ago

dolphin-mistral

The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.

7b

674.4K Pulls 120 Tags Updated 1 year ago

dolphincoder

A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.

7b 15b

330.6K Pulls 35 Tags Updated 1 year ago

tinydolphin

An experimental 1.1B parameter model trained on the new Dolphin 2.8 dataset by Eric Hartford and based on TinyLlama.

1.1b

314.4K Pulls 18 Tags Updated 2 years ago

megadolphin

MegaDolphin-2.2-120b is a transformation of Dolphin-2.2-70b created by interleaving the model with itself.

120b

177.2K Pulls 19 Tags Updated 2 years ago

deepseek-r1

DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.

tools thinking 1.5b 7b 8b 14b 32b 70b 671b

77.7M Pulls 35 Tags Updated 7 months ago

aeline/phil

Uncensored version of dolphin family models 🐊

92K Pulls 1 Tag Updated 2 months ago

uandinotai/dolphin-uncensored

create uncensored everything

tools

2,143 Pulls 1 Tag Updated 5 months ago

richardyoung/dolphin-yi-34b-heretic

Exceptional conversational AI with 77.4 MMLU score, offering natural dialogue and multi-domain expertise without any content filtering.

259 Pulls 1 Tag Updated 2 months ago

angel7x/meddolphin

A fine-tuned Dolphin3 model (unrestricted version of Llama) from https://ollama.com/library/dolphin3 (dolphin3:latest) that has been trained on the OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B dataset from huggingface.

169 Pulls 1 Tag Updated 1 month ago