You can deploy this model and start earning money today!

webkul/
Aureus-gemma-finetuned

Name: Aureus-gemma-finetuned
Availability: InStock

safetensors

gemma3_text

Views

No views yet

Aureus ERP Fine-Tuned Gemma-3 Model

This is a fine-tuned version of the Gemma-3 open-source LLM, specialized for answering questions based on AureusERP developer documentation.

Aureus ERP is an open-source Enterprise Resource Planning (ERP) platform built with Laravel. It offers a modular and scalable architecture for businesses of all sizes to manage various aspects of their operations, including inventory, sales, projects, and more. Aureus ERP is designed to be flexible, customizable, and developer-friendly, allowing businesses to tailor the platform to their specific needs.

🔧 Model Details

Base Model: gemma-3b
Fine-tuned On: Internal AureusERP Developer Docs
Precision: Float16 (merged & optimized for deployment)
Tokenizer: Same as base model
Training Objective: Supervised fine-tuning with synthetically generated QA pairs for LLM alignment

🧠 Use Case

This model is optimized for answering technical questions related to AureusERP, such as:

Filament integration and actions
Module architecture (e.g., FollowerAction, notifications, dev hooks)
Deployment/configuration steps
Developer-specific usage patterns

📁 Data Source

Training data was automatically generated using Gemini 2.5-flash and then curated.

📄 Source: Internal AureusDevDocs (markdown)
🤖 Process: QA pairs extracted from docs using Gemini
🔢 Format: JSON list of question-answer pairs

🔌 How to Use

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("webkul/Aureus-gemma-finetuned", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("webkul/Aureus-gemma-finetuned")

prompt = "How can I add followers using AureusERP FollowerAction?"
inputs = tokenizer(prompt, return_tensors="pt")

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

👥 Maintained By

Webkul AI Research Team https://webkul.com