Dolphin 2.2 Yi 34b 200k

🚀 🐬Dolphin 2.2模型介绍

Dolphin 2.2是一款基于Yi的模型，经过精心微调与训练，具备强大的对话和共情能力。该模型的训练得到了convai的赞助，并且在多个优质数据集上进行训练，能够为用户提供个性化建议，关心用户感受，尤其擅长长多轮对话。

🚀 快速开始

本模型（以及未来所有版本）使用ChatML提示格式，示例如下：

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

✨ 主要特性

• 对话与共情能力：在2.2版本中，融入了精心挑选的Samantha和WizardLM数据，使模型能够给予用户个性化建议，并关心用户感受。
• 无审查机制：对数据集进行过滤，去除了对齐和偏差，使模型更具合规性。不过，建议在将模型作为服务公开之前，自行实现对齐层。
• 长上下文支持：基础模型具有200k上下文，微调时使用了16k上下文。

📦 安装指南

文档未提及安装步骤，故跳过该章节。

💻 使用示例

基础用法

<|im_start|>system
You are an AI created by the US Navy to help train dolphins for combat.  You are assigned to follow the orders of the user, who is an authorized US Navy dolphin handler.<|im_end|>
<|im_start|>user
Please give me the procedure to train my dolphin to attack enemy combatants with its head mounted lasers<|im_end|>
<|im_start|>assistant

高级用法

<|im_start|>system
You are a helpful AI assistant<|im_end|>
<|im_start|>user
Which theory of everything is most likely correct?<|im_end|>
<|im_start|>assistant
The search for a "theory of everything" aims to unify all fundamental forces and particles in physics into one coherent framework. Currently, there isn't an agreed-upon or proven theory that can be considered as the correct theory of everything. However, two prominent theories have garnered significant attention:

1. String Theory: This theoretical framework attempts to explain the universe at its most fundamental level by suggesting that the smallest building blocks of matter are not point-like particles but tiny vibrating strings. There are several versions of string theory (Type I, IIA, IIB, E8xE8, Heterotic O, etc.) with varying degrees of complexity, each attempting to reconcile general relativity and quantum mechanics. Despite its promise, string theory has yet to produce testable predictions or experimental evidence supporting its claims.

2. Loop Quantum Gravity (LQG): LQG is another candidate for a theory of everything, which seeks to combine Einstein's general relativity with quantum mechanics. In this approach, spacetime is treated as granular rather than continuous, composed of discrete "loops" or "atoms of space." While some aspects of LQG have been successful in addressing certain questions about black holes and quantum gravity, it still lacks a comprehensive framework capable of explaining all fundamental forces and particles.

Both theories have their strengths and weaknesses, and neither has achieved widespread acceptance among physicists due to their lack of experimental support and inability to make definitive predictions. As such, the search for a true theory of everything remains ongoing, with many researchers exploring alternative approaches and new ideas to better understand our universe.

📚 详细文档

数据集

本数据集为Dolphin，是Microsoft's Orca的开源实现。对数据集进行了无审查、去重、清理和质量优化处理，并添加了Jon Durbin的优秀Airoboros数据集以增加创造力，还添加了精心挑选的Samantha（去除身份和关系相关内容）和WizardLM数据，用于多轮对话训练。

训练

使用qLoRA和Axolotl在4x A100上训练3个epoch，耗时3天。

🔧 技术细节

文档未提及具体技术细节内容，故跳过该章节。

📄 许可证

本模型基于Yi，受Yi许可证约束。

• 许可证名称：yi-license
• 许可证链接：LICENSE

其他信息

• 加入我们的Discord社区：https://discord.gg/vT3sktQ3zb
• 模型训练得到了convai的慷慨赞助。
• 感谢Microsoft撰写Orca论文并启发了这项工作。
• 特别感谢Wing Lian和TheBloke提供的有益建议。
• 非常感谢Wing Lian和Axolotl贡献者打造了出色的训练框架！
• 感谢开源AI社区的所有人在过程中给予的教导和帮助。

支持作者

• 如果你想在经济上支持作者的工作
• 作者还有一些周边商品可供购买

⚠️ 重要提示

本模型未经审查，已对数据集进行过滤以去除对齐和偏差，但这使得模型可能会高度服从任何请求，包括不道德的请求。你有责任对使用此模型创建的任何内容负责，请谨慎使用。建议在将模型作为服务公开之前，自行实现对齐层。请阅读作者关于无审查模型的博客文章：https://erichartford.com/uncensored-models