Llama 3 Cat 8b Instruct V1

🚀 llama-3-cat-8b-instruct-v1

llama-3-cat-8b-instruct-v1 是一个基于 Llama 3 8B 的微调模型，专注于系统提示保真度、实用性和角色沉浸感。该模型旨在最大程度遵循系统提示，无论何种情况都能提供有用信息，并在给定场景中实现最大程度的角色沉浸（角色扮演）。

✨ 主要特性

• 系统指令保真度：高度尊重系统提示，严格按照提示要求生成回复。
• 思维链（COT）：能够进行连贯的推理和思考，逐步解决问题。
• 角色沉浸感：在角色扮演场景中，提供高度沉浸的角色体验。
• 生物科学和通用科学实用性：在生物科学和通用科学领域提供有价值的信息和帮助。

📦 安装指南

文档未提及安装步骤，故跳过此章节。

💻 使用示例

基础用法

<|begin_of_text|>Below is a conversation between an user and an AI assistant. The ai assistant gives response regarding user's questions. USER: user: Given the task definition and input, reply with output. In this task, you are given a question and an answer, you would be asked to create the sentence based on the Question-Answer provided. It should be contained within the Question-Answer provided.

Question: What type of diseases in humans are caused by protozoa? Answer: protist diseases
ASSISTANT: AI: Task Explanation:
In this task, you are asked to create a sentence using the given question and the provided answer. The sentence you create should include the information from both the question and the answer in a concise and coherent manner.
Guidelines:
1. Read the given question and answer carefully.
2. Combine the information from the question and answer to create a new sentence.
3. Make sure your new sentence contains both the question's information and the answer provided.
4. Check your sentence for proper grammar and punctuation.
Steps to find the answer:
1. Read the question: "What type of diseases in humans are caused by protozoa?"
2. Read the answer: "protist diseases"
3. Combine the information from the question and answer to create a new sentence: "In humans, protist diseases are caused by protozoa."
4. Double-check the sentence for proper grammar and punctuation, and make necessary adjustments if needed.
Final Output:
In humans, protist diseases are caused by protozoa.<|end_of_text|>

高级用法

文档未提及高级用法相关代码示例，故跳过此部分。

📚 详细文档

模型相关人员

• 数据集构建者：Dr. Kal'tsit (Kat)
• 训练者/资助者：SteelSkull
• 推动者：Potatooff

数据集准备

从 Huggingface 系统地提取包含指令 - 响应对的数据集。专门针对高质量和有用的响应训练了一个 GPT 模型，作为标准模型。对数据集进行了长度和思维链响应过滤，还从 Chat Doctor 提取了与健康相关的数据，倾向于详细和逐步的诊断。

模型训练

使用 1 个 A100 GPU 训练 6 天，共 4 个 epoch。

提示格式

• 设置/上下文/指令：由 @Anthonyg5005 提供
• Cat 8B Gen Settings
• Cat 8b Context
• Cat 8b Instruct

量化模型

• bartowski/llama-3-cat-8b-instruct-v1-GGUF

模型展示

模型在灰色区域进行思维链推理，黑色区域为计算得出的响应。请注意，这种行为是通过系统卡指令展示系统卡保真度，并非模型微调的结果。

评估结果

详细结果可查看 此处。

🔧 技术细节

文档未提供具体技术实现细节，故跳过此章节。

📄 许可证

本模型使用 Llama3 许可证。