CoolFace
Modelpublic

odenmehmet/trobject_llama-3_8b_unsloth_2x_faster_finetuning

sourceHugging Faceapache-2.0updated 5mo agoView on Hugging Face
0likes20downloads
Model Card

TRObject LLaMA-3 8B Code Generation Model

This repository contains a domain-specific fine-tuned LLaMA-3 8B model for generating TRObject code from natural language prompts.

TRObject is used in the Clomosy mobile application development platform. The goal of this model is to help users generate copy-ready TRObject code snippets for common mobile UI and application-development tasks.

Project Motivation

General-purpose LLMs do not reliably understand TRObject syntax, Clomosy-specific UI patterns, or platform-specific development workflows.

To address this gap, I created a custom instruction-style dataset and fine-tuned a LLaMA-3 8B model for TRObject code generation.

The project focuses on:

  • —Natural language to TRObject code generation
  • —Mobile UI component generation
  • —Form, button, input, event, and database-related code snippets
  • —Domain-specific adaptation of a general-purpose LLM

Base Model and Fine-Tuning

  • —Base model: unsloth/llama-3-8b-bnb-4bit
  • —Architecture: LLaMA-3 8B
  • —Fine-tuning method: Supervised fine-tuning with LoRA adapters
  • —Optimization: 4-bit quantization with Unsloth
  • —Libraries: Hugging Face Transformers, TRL, Unsloth, PEFT/LoRA

Dataset

The model was fine-tuned on a custom instruction-style dataset containing natural language prompts and corresponding TRObject code outputs.

Dataset format:

ColumnDescription
inputNatural language instruction
outputCorresponding TRObject code snippet

The dataset includes examples for:

  • —Form creation
  • —Button and input field creation
  • —Click event definitions
  • —Login/register UI flows
  • —SQLite query usage
  • —ListView data loading
  • —UI component configuration

Dataset repository:

odenmehmet/TRObject-Dataset-Test

Example Prompts and Outputs

Example 1 — Create a form input

Prompt

text
Form oluştur ve bir edit alanı ile buton ekle.

Output style

text
MyForm = TclForm.Create(Self);
testEdit = MyForm.AddNewEdit(MyForm,'testEdit','Barcode here ...');
testEdit.Align = alTop;
testEdit.Height = 40;

testBtn = MyForm.AddNewButton(MyForm,'testBtn','Scan Barcode...');
testBtn.Align = alCenter;
testBtn.Height = 100;
testBtn.Width = 200;
MyForm.AddNewEvent(testBtn,tbeOnClick,'BtnOnClick');

Example 2 — Add a button with a click event

Prompt

text
Buton ekle ve ona bir tıklama olayı ekle.

Output style

text
testBtn = MyForm.AddNewButton(MyForm,'testBtn','Scan Barcode...');
testBtn.Align = alCenter;
testBtn.Height = 100;
testBtn.Width = 200;
MyForm.AddNewEvent(testBtn,tbeOnClick,'BtnOnClick');

Example 3 — Create a login screen

Prompt

text
Bir giriş ekranı oluştur ve e-posta ve parola alanlarını ekle.

Output style

text
myForm = TclForm.Create(Self);

EmailEdit = myForm.AddNewProEdit(MainPnl, 'EmailEdit', 'E-posta');
EmailEdit.Align = alTop;
EmailEdit.Height = 50;

ParolaEdit = myForm.AddNewProEdit(MainPnl, 'ParolaEdit', 'Parola');
ParolaEdit.Align = alTop;
ParolaEdit.Height = 50;
ParolaEdit.Password = True;

Example 4 — Create a simple UI flow

Prompt

text
Bir form üzerinde kullanıcıdan isim alıp butona basınca işlem yapacak basit bir arayüz oluştur.

Output style

text
MyForm = TclForm.Create(Self);

NameEdit = MyForm.AddNewEdit(MyForm, 'NameEdit', 'İsim giriniz');
NameEdit.Align = alTop;
NameEdit.Height = 40;

SubmitBtn = MyForm.AddNewButton(MyForm, 'SubmitBtn', 'Gönder');
SubmitBtn.Align = alTop;
SubmitBtn.Height = 45;

MyForm.AddNewEvent(SubmitBtn, tbeOnClick, 'SubmitBtnOnClick');

Intended Use

This model is intended for:

  • —TRObject code generation experiments
  • —Domain-specific LLM fine-tuning demonstrations
  • —Educational use in custom code-generation workflows
  • —Assisting developers with repetitive Clomosy/TRObject UI patterns

Limitations

This model is experimental and should not be used as a fully autonomous code generator without human review.

Known limitations:

  • —May generate syntactically incorrect TRObject code for complex requests
  • —May hallucinate unsupported components or APIs
  • —Works better on patterns similar to the training data
  • —Requires developer validation before use in production
  • —Dataset size is limited, so generalization may be weak outside known TRObject patterns

Recommended Usage

Use the model as an assistant for generating draft TRObject snippets. All generated code should be manually reviewed and tested inside the Clomosy/TRObject development environment.

Data Safety Note

The dataset and examples should only include sanitized, non-sensitive, and non-confidential code samples.

Do not use private credentials, production data, customer data, or proprietary business logic in public examples.

Developer

Developed by Mehmet Öden as part of an AI/LLM internship project focused on domain-specific code generation for TRObject and Clomosy-style mobile application development.