🚀 🐬Dolphin 2.2模型介紹
Dolphin 2.2是一款基於Yi的模型,經過精心微調與訓練,具備強大的對話和共情能力。該模型的訓練得到了convai的贊助,並且在多個優質數據集上進行訓練,能夠為用戶提供個性化建議,關心用戶感受,尤其擅長長多輪對話。
🚀 快速開始
本模型(以及未來所有版本)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
- 對話與共情能力:在2.2版本中,融入了精心挑選的Samantha和WizardLM數據,使模型能夠給予用戶個性化建議,並關心用戶感受。
- 無審查機制:對數據集進行過濾,去除了對齊和偏差,使模型更具合規性。不過,建議在將模型作為服務公開之前,自行實現對齊層。
- 長上下文支持:基礎模型具有200k上下文,微調時使用了16k上下文。
📦 安裝指南
文檔未提及安裝步驟,故跳過該章節。
💻 使用示例
基礎用法
<|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
高級用法
<|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.
📚 詳細文檔
數據集
本數據集為Dolphin,是Microsoft's Orca的開源實現。對數據集進行了無審查、去重、清理和質量優化處理,並添加了Jon Durbin的優秀Airoboros數據集以增加創造力,還添加了精心挑選的Samantha(去除身份和關係相關內容)和WizardLM數據,用於多輪對話訓練。
訓練
使用qLoRA和Axolotl在4x A100上訓練3個epoch,耗時3天。
🔧 技術細節
文檔未提及具體技術細節內容,故跳過該章節。
📄 許可證
本模型基於Yi,受Yi許可證約束。
其他信息
- 加入我們的Discord社區:https://discord.gg/vT3sktQ3zb
- 模型訓練得到了convai的慷慨贊助。
- 感謝Microsoft撰寫Orca論文並啟發了這項工作。
- 特別感謝Wing Lian和TheBloke提供的有益建議。
- 非常感謝Wing Lian和Axolotl貢獻者打造了出色的訓練框架!

- 感謝開源AI社區的所有人在過程中給予的教導和幫助。
支持作者
⚠️ 重要提示
本模型未經審查,已對數據集進行過濾以去除對齊和偏差,但這使得模型可能會高度服從任何請求,包括不道德的請求。你有責任對使用此模型創建的任何內容負責,請謹慎使用。建議在將模型作為服務公開之前,自行實現對齊層。請閱讀作者關於無審查模型的博客文章:https://erichartford.com/uncensored-models
屬性 |
詳情 |
數據集 |
ehartford/dolphin、jondurbin/airoboros-2.2.1、ehartford/samantha-data、ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split |
語言 |
en |
許可證名稱 |
yi-license |
許可證鏈接 |
LICENSE |