Beta

Explore
Marketplace
Neural Labs
Chat
Wallet
Docs

Beta

Explore Marketplace Neural Labs Wallet Docs

Build

Manage

My assets Manage wallet Organization

Community

Discord X (Twitter)Telegram

Docs Privacy Policy Terms and Conditions

Proud member of

Proud member of

Docs Cookie Policy

Privacy Policy Terms and Conditions

© 2026 AlphaNeural AI. All rights reserved.

trainer-eksperimen-1 – AI Model by mahfudl26 | AlphaNeural AI

You can deploy this model and start earning money today!

mahfudl26/
trainer-eksperimen-1

like

0

endpoints_compatible

Views

No views yet

LLaMA 3.1 QLoRA - Trainer Eksperimen 1

Model Description

Model ini merupakan hasil fine-tuning dari model LLaMA 3.1 8B menggunakan teknik QLoRA dengan dataset Alpaca GPT4 Indonesian.

Model dirancang sebagai asisten AI untuk menjawab pertanyaan dalam Bahasa Indonesia secara akurat dan natural.

Developed by: Mahfudl Awaludin
Model type: Causal Language Model
Language: Indonesian
Finetuned from: unsloth/Llama-3.1-8B

Training Details

Dataset

Dataset: Ichsan2895/alpaca-gpt4-indonesian
Format: Instruction - Response
Bahasa: Indonesia

Training Method

Technique: QLoRA (4-bit quantization)
Framework: Transformers + TRL + PEFT
Optimizer: paged_adamw_8bit

Hyperparameters

Batch size: 1
Gradient accumulation: 8
Learning rate: 2e-4
Max steps: 800
Max length: 256

Usage

python

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("mahfudl26/trainer-eksperimen-1")
tokenizer = AutoTokenizer.from_pretrained("mahfudl26/trainer-eksperimen-1")

prompt = "Apa itu machine learning?"
inputs = tokenizer(prompt, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0]))