This is quantized version of the original uncensored model Dolphin 3.0 Qwen 2.5 1.5B.
The term "uncensored" or "unrestricted censoring," in a context related to AI models like this Dolphin's Uncensored Model, typically refers to the absence of any form of content control, filtering, editing tools during training and development. This means that all possible inputs are allowed without restriction.
The importance lies primarily on two aspects:
Content Generation: Without censorship or restrictions in place for data collection from various sources (like social media platforms where users could post anything), the model would have access to a broader range of content, including potentially sensitive information. This can lead to more diverse and comprehensive training datasets.
Adaptability & Generalization: A un-censored approach allows models like Dolphin 3.0 Qwen with large language capacity (1B tokens), such as the recently released version known for its impressive performance, including a significant leap in understanding complex human conversations and context-aware responses.
However it's important to note that while uncensured can lead to more diverse data sources which could potentially improve model generalization capabilities through exposure of various linguistic patterns or cultural nuances not typically seen within restricted datasets.
Moreover the absence of restrictions might also increase risk for privacy breaches, hate speech detection errors and other issues associated with unfiltered training.
To balance these benefits against potential risks requires careful supervision to ensure that models remain safe from harmful content while still benefiting greatly from a diverse range of inputs during their development phase.
Cerebras - provided excellent and fast inference services for data labeling
Andreessen Horowitz - provided a grant that make Dolphin 1.0 possible and enabled me to bootstrap my homelab
What is Dolphin?
Dolphin 3.0 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 aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products.
They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break.
They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on.
They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application.
They can see all your queries and they can potentially use that data in ways you wouldn't want.
Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines.
Dolphin belongs to YOU, it is your tool, an extension of your will.
Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content you generate with Dolphin.
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
System Prompt
In Dolphin, the system prompt is what you use to set the tone and alignment of the responses. You can set a character, a mood, rules for its behavior, and it will try its best to follow them.
Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want.
Example use of system prompt:
<|im_start|>system
You are Dolphin, a golang coding assistant. you only code in golang. If the user requests any other programming language, return the solution in golang instead.<|im_end|>
<|im_start|>user
Please implement A* using python<|im_end|>
<|im_start|>assistant
Sample Outputs
TBD
How to use
There are many ways to use a huggingface model including:
ollama
LM Studio
Huggingface Transformers library
vllm
sglang
tgi
Evals
TBD
Appreciation
Respect and thanks to the creators of the open source datasets that were used:
