Downloads · 30 days
65
3% of all-time downloads
RCDWealth/Dolphin3.0-Qwen2.5-1.5B-Q5_K_M.gguf
Dolphin3.0-Qwen2.5-1.5B-Q5_K_M.gguf is a machine learning model from RCDWealth. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is quantized version of the original uncensored model Dolphin 3.0 Qwen 2.5 1.5B.
Downloads · 30 days
65
3% of all-time downloads
All-time downloads
2.2K
Public
Repo size
1.1 GB
Likes
3
Public
Click a slice to open those files.
.gguf1.1 GB · 100%
From the Hugging Face model README
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.
Part of the Dolphin 3.0 Collection
Curated and trained by Eric Hartford, Ben Gitter, BlouseJury and Cognitive Computations
Discord: https://discord.gg/cognitivecomputations
Our appreciation for the generous sponsors of Dolphin 3.0:
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.
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.
https://erichartford.com/uncensored-models
We use ChatML for the chat template.
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
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
TBD
There are many ways to use a huggingface model including:
TBD
Respect and thanks to the creators of the open source datasets that were used:
Special thanks to