Scribd
Upload
39 views3 pages

LLM Installation

Uploaded by

eswarannihil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
39 views3 pages

LLM Installation

Uploaded by

eswarannihil
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

LLM installation instructions

1 Introduction
Learner of local models (LLM) is implemented in Java. The algorithm uses
Prolog as a module for calculating feature values. The communication with
Prolog is done by means of a 2p.jar located in the library. It is fully integrated
and, therefore, there is no demand on users to set anything for this interface
to work properly.

2 Prerequisite
The user needs Java Runtime Environment (JRE) 1.7 to run the code and
Java Development Kit (JDK) 1.7 or newer to compile it. For compiling the
code and generating executable jar, the user needs Apache Maven 3.0.5 or
newer. For JRE, JDK and Apache Ant, the most stable versions for your
platform are the best choice.

3 Instructions
The following installation instructions are valid for all platforms that support
Java and Apache Maven. In order to generate needed executable jar, go to the
main folder “HybridRDN”. Then run the following command:

mvn clean compile assembly:single

This command will compile all the classes and generate an executable jar
llm.jar in folder target.

1
4 Test
In order to test whether the executable jar is functional perform this little test
in the terminal. All the needed files are provided in folder UniversityExample
/data university .

java -jar target/llm.jar -input


UniversityExample/data university/ -output
UniversityExample/results/ -predicates intelligence
This command will run the llm learner using the main class of the default
hybrid.custom structure learner.Custom StructureLearner . Whenthe
programfinishestheusershouldhave resultsfolderwithresultsfor intelligence
predicatein UniversityExample folder.Theinformationaboutthesefilesis
given in the manual provided in this folder as well. This runnable jar executes
mainmethodin custom structure learner.Custom StructureLearner .This
method represents the guideline on how to run our structure learning algo-
rithm.

5 Wherefromhere?
As mentioned before, the runnable jar file created above runs the main class of
hybrid.custom structure learner.Custom StructureLearner class. There
are some important parts of this class that a user can change to run the al-
gorithm for the network and data he/she wants:

1. Network hybrid university=new Network();


ntw=hybrid university.defineApplicationNetwork(1);
Here we create a network class that has random variable declarations
(RVDs). In this default class we give RVDs of the University domain.
In order to create one from scratch, the user should look into the
manual.pdf where we provided detailed instructions.

2. Data d training=dataLoader.loadData(parameters.input path+"/train


"interp", "pl",ntw);
Data d validation=dataLoader.loadData(parameters.input path+"/val
"interp", "pl",ntw);
Data d test=dataLoader no subsampling.loadData(parameters.input

2
"/test/","interp", "pl",ntw);
The user should specify the data used for his/her purposes.
The rest of the main class should stay more or less the same. When the
classes are changed for the purposes of the user, a new executable jar should
be made with the procedure explained above.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy