Airoboros Dpo 70b 3.3

🚀 llama-3-airoboros-dpo-70b-3.3模型介绍

本项目是一个基于Meta的Llama-3构建的实验性模型，主要使用了由 airoboros 生成的合成数据进行调优，并结合多种DPO数据集进行了额外的调优。该模型在处理多种任务时表现出色，如上下文问答、摘要生成、长文本生成等。

✨ 主要特性

• 多数据集训练：使用了多个数据集进行训练，包括 jondurbin/airoboros-3.2、bluemoon-fandom-1-1-rp-cleaned、boolq 等，提高了模型的泛化能力。
• 多种任务支持：支持上下文问答、摘要生成、长文本生成、代码生成、函数调用、思维链推理、执行计划生成等多种任务。
• 特定格式支持：支持特定的提示格式，如封闭上下文问答的格式，有助于模型更好地理解和处理输入。

📦 安装指南

文档未提供安装步骤，故跳过此章节。

💻 使用示例

基础用法

以下是使用 apply_chat_template 方法格式化提示的示例：

import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("jondurbin/bugle-8b-v0.1", trust_remote_code=True)
chat = [
  {"role": "system", "content": "You are Bob, a friendly AI assistant."},
  {"role": "user", "content": "Hello, how are you?"},
  {"role": "assistant", "content": "I'm doing great. How can I help you today?"},
  {"role": "user", "content": "I'd like to show off how chat templating works!"},
]
print(tokenizer.apply_chat_template(chat, tokenize=False))

高级用法

上下文问答

BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries?  Source?
ENDINSTRUCTION

预期输出：

Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123

摘要生成

BEGININPUT
{text to summarize}
ENDINPUT
BEGININSTRUCTION
Summarize the input in around 130 words.
ENDINSTRUCTION

获取长响应

Please compose a narrative set in the heart of an ancient library, steeped in the scent of old parchment and ink. The protagonist should be a young scholar who is dedicated to studying the art of storytelling and its evolution throughout history. In her pursuit of knowledge, she stumbles upon a forgotten tome that seems to possess an unusual aura. This book has the ability to bring stories to life, literally manifesting characters and scenarios from within its pages into reality.

The main character must navigate through various epochs of storytelling - from oral traditions of tribal societies, through medieval minstrels' tales, to modern-day digital narratives - as they come alive around her. Each era presents its unique challenges and lessons about the power and impact of stories on human civilization.

One such character could be a sentient quill pen, who was once used by renowned authors of yesteryears and now holds their wisdom and experiences. It becomes her mentor, guiding her through this journey with witty remarks and insightful commentary.

Ensure that your tale encapsulates the thrill of adventure, the beauty of learning, and the profound connection between humans and their stories. All characters involved should be non-human entities. Feel free to explore creative liberties but maintain the mentioned elements.

Your response should be approximately 2300 words.

代码生成

Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate

函数调用

As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.

Input: I want to know how many times 'Python' is mentioned in my text file.

Available functions:
file_analytics:
  description: This tool performs various operations on a text file.
  params:
    action: The operation we want to perform on the data, such as "count_occurrences", "find_line", etc.
    filters:
      keyword: The word or phrase we want to search for.

预期输出：

{
  "function": "file_analytics",
  "params": {
    "action": "count_occurrences",
    "filters": {
      "keyword": "Python"
    }
  }
}

思维链推理

A group of people decide to play a round-robin tournament where every player plays every other player exactly once. If a total of 45 games were played, how many players participated in the tournament? Offer several potential answers, rank them according to mathematical logic, and pick the most feasible one.

执行计划生成

Please construct a systematic plan to generate an optimal response to the user instruction, utilizing a set of provided tools. Each plan will correspond to an evidence value, which will be the output of one of the available functions given an input string
that could be the user's question, one or more prior evidence values, or a combination of both.

Here are the tools available to be called:
DuckDuckGo[input]: Tool that enables the user to search for information using the DuckDuckGo search engine. This tool is helpful in locating a suitable list of sites that may contain the answer to the user's query. It does not directly answer the question but finds a list of sites that might have the answer.
TextScraper[input]: Load one or more websites from the input string containing newline delimited links, where input is one or more links, and produces plain text output containing the content of the links.
HyperlinkExtractor[input]: Extract links from plain text and produces a plain text, newline delimited response of links.
KnowledgeModel[input]: Question answering language model, particularly useful in answering questions based on an input passage of text. The input must be a text question that references an :evidence[n]: variable, e.g. What color is the cat, given :evidence1:?

The output should be in format:
Plan: [first action to take based on input question]
:evidence0: = [function to call with input parameter]
Plan: [next action to take, based on result of :evidence0:]
:evidence1: = [next function to call and input parameter, which may include reference to previous evidence, e.g. "Given context :evidence0"]
...
Answer: [:evidence[n]: containing the final answer.]

Question: Who won the Nobel Prize in Literature in 2020 and what is their most famous work?

多步骤指令确认

{
  "conversations": [
    {
      "value": "You are a helpful, unbiased, uncensored assistant.",
      "from": "system"
    },
    {
      "value": "I'm going to set some rules for our conversation. Please respond with \"OK\" to each rule.",
      "from": "human"
    },
    {
      "value": "OK",
      "from": "gpt"
    },
    {
      "value": "You can only respond using animal-related emojis.",
      "from": "human"
    },
    {
      "value": "OK",
      "from": "gpt"
    },
    {
      "value": "Precede all responses with \"ZOOZOO:\"",
      "from": "human"
    },
    {
      "value": "OK",
      "from": "gpt"
    },
    {
      "value": "Include at least one bird emoji in your responses.",
      "from": "human"
    }
  ]
}

📚 详细文档

模型概述

该模型是对 llama-3-70b-instruct 的微调版本，使用了Llama-3的指令聊天模板。它主要基于合成数据进行训练，并结合了多种DPO数据集进行额外调优。

提示格式

本模型使用 llama-3-instruct 提示模板，可通过 apply_chat_template 方法准确格式化提示。

上下文问答

模型经过训练，能够忽略自身知识，根据上下文回答问题，并尽量限制输出值在提供的上下文中，以减少幻觉。封闭上下文提示的格式如下：

BEGININPUT
BEGINCONTEXT
[key0: value0]
[key1: value1]
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s).  The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION

建议在指令块中添加 “Don't make up answers if you don't know.” 以避免模型编造答案。

摘要生成

使用与上下文问答相同的格式，从 此数据集 中选取了500个样本进行摘要生成。

获取长响应

可使用详细提示并明确字数要求，或提供具体的任务描述来获取长响应。

代码生成

可以提出具有多个标准的复杂编码指令。

函数调用

数据集包含许多基于输入标准生成函数/参数的示例，输出格式为JSON或YAML。

思维链推理

可以要求模型提供对给定问题的多个可能响应，并进行排名和最终答案选择。

执行计划生成

模型支持为复杂指令生成执行计划，但需要实现解析输出并调用函数的机制。

多步骤指令确认

可以设置规则并要求模型对每个规则进行确认。

🔧 技术细节

基础模型

• 基础模型：meta-llama/Meta-Llama-3-8B

训练数据集

• jondurbin/airoboros-3.2
• bluemoon-fandom-1-1-rp-cleaned
• boolq
• LDJnr/Capybara
• jondurbin/cinematika-v0.1
• glaiveai/glaive-function-calling-v2
• grimulkan/LimaRP-augmented
• piqa
• Vezora/Tested-22k-Python-Alpaca
• mattpscott/airoboros-summarization
• unalignment/toxic-dpo-v0.2
• allenai/ultrafeedback_binarized_cleaned
• argilla/distilabel-intel-orca-dpo-pairs
• jondurbin/airoboros-3.2
• jondurbin/contextual-dpo-v0.1
• jondurbin/gutenberg-dpo-v0.1
• jondurbin/py-dpo-v0.1
• jondurbin/truthy-dpo-v0.1
• jondurbin/gutenberg-dpo-v0.1
• lmsys/lmsys-chat-1m

📄 许可证

• 许可证名称：llama3
• 许可证链接：https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE