渐得如意概念演示版 #2
Magic-Abracadabra
announced in
Announcements
Replies: 1 comment
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
关于本包(About This Package)
这是一个概念演示EXE,等到全面开源阶段时,本项目将不再采取EXE文件的分发形式。If allowed, we may open an English version as well. 我们欢迎大家用自己的母语重构本平台(语音模式下,可以使用方言)。
说明
重要声明
官方教程:https://github.com/Magic-Abracadabra/DAHSF/wiki/渐得如意智能自动化办公平台——定义属于你的咒语
平台简介
平台功能与特色
平台的技术原理
Digestion Algorithm in Hierarchical Symbolic Forests: A Fast Text Normalization Algorithm and Semantic Parsing Framework for Specific Scenarios and Lightweight Deployment
Currently, the DAHSF is protected. Any external use is strictly prohibited, except for academic and research purposes. Commercial use requires explicit authorization contracts. Any use for malicious activities, cyberattacks, or black-hat operations, is strictly forbidden.
More Information
Abstract
Text Normalization and Semantic Parsing have numerous applications in natural language processing, such as natural language programming, paraphrasing, data augmentation, constructing expert systems, text matching, and more. Despite the prominent achievements of deep learning in Large Language Models (LLMs), the interpretability of neural network architectures is still poor, which affects their credibility and hence limits the deployments of risk-sensitive scenarios. In certain scenario-specific domains with scarce data, rapidly obtaining a large number of supervised learning labels is challenging, and the workload of manually labeling data would be enormous. Catastrophic forgetting in neural networks further leads to low data utilization rates. In situations where swift responses are vital, the density of the model makes local deployment difficult and the response time long, which is not conducive to local applications of these fields. Inspired by the multiplication rule, a principle of combinatorial mathematics, and human thinking patterns, a multilayer framework along with its algorithm, the Digestion Algorithm in Hierarchical Symbolic Forests (DAHSF), is proposed to address these above issues, combining text normalization and semantic parsing workflows. The Chinese Scripting Language "Fire Bunny Intelligent Development Platform V2.0" is an important test and application of the technology discussed in this paper. DAHSF can run locally in scenario-specific domains on little datasets, with model size and memory usage optimized by at least two orders of magnitude, thus improving the execution speed, and possessing a promising optimization outlook.
Significant Declaration
Due to very limited resources (esp. equipments), the data (not including DAHSF) in this table was generated by ChatGLM-4.
产品功能
本平台可学习用户的词汇、(最好符合中文语法的)句法,并且允许用户使用个性化但相对自由多样的表述方式下达用户自己定义的Python指令。本平台既可以通过“渐得如意”直接命令交互,又可以用“渐得如意”打开中文命令脚本。
价值主张
你的创意,你的数据,左右由你——渐得如意智能自动化办公平台
简短描述
功能上,本平台可学习用户的词汇、(最好符合中文语法的)句法,并且允许用户使用个性化但相对自由多样的表述方式下达用户自己定义的Python指令。本平台既可以通过“渐得如意”直接命令交互,又可以用“渐得如意”打开中文命令脚本。
特点上,本平台,作为这类架构的典型应用场景,延续了这类架构的特点。本平台因其所采用的架构,能在CPU上学习、本地运行、离线解析命令(除非自定义的指令内容需要联网)。一旦学习完毕,执行知识库内的指令迅速且较为稳定,可靠度高。模型架构之外,本平台使用中文作为脚本语言,无需手动编译就可以执行脚本。
关键字
RPA、自定义中文高级计算机语言、本地学习、可审计运行、新派Web3.0
版权和商标信息
本平台的基础智能架构与算法受版权保护且源码(https://github.com/Magic-Abracadabra/DAHSF )暂无协议——其为层次意蕴林(DAHSF:https://www.alphaxiv.org/abs/2412.14054 )的实际应用(论文使用协议:https://creativecommons.org/licenses/by-nc-nd/4.0/ )
其他许可条款
3.1. GitHub:https://github.com/Magic-Abracadabra
3.2. Codeberg:https://codeberg.org/Magic-Abracadabra
3.3. Hugging Face:https://huggingface.co/Magic-Abracadabra
3.4. Vimeo:https://vimeo.com/magicabracadabra
3.5. Instagram:https://www.instagram.com/magic_abracadabra_ins/
3.6. 火山引擎:https://developer.volcengine.com/user/2930619025728955
3.7. 魔搭社区:https://www.modelscope.cn/profile/MagicAbracadabra
3.8. 稀土掘金:https://juejin.cn/user/458920202081724
开发者
Magic-Abracadabra
近似大小
17.2 MB
This discussion was created from the release 渐得如意概念演示版.
All reactions