mrfadlika/dicoding-rag-gemma-raffi

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:2.6BQuant:BF16Context Size:8kPublished:Jul 22, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The mrfadlika/dicoding-rag-gemma-raffi is a 2.6 billion parameter Gemma-2 model, developed by mrfadlika, fine-tuned using Unsloth and Huggingface's TRL library. This model was trained significantly faster, leveraging Unsloth's optimization for efficient fine-tuning. It is designed for applications requiring a compact yet capable language model, particularly where rapid training and deployment are beneficial.

Loading preview...

Model Overview

The mrfadlika/dicoding-rag-gemma-raffi is a 2.6 billion parameter language model based on the Gemma-2 architecture. Developed by mrfadlika, this model was fine-tuned using the Unsloth library in conjunction with Huggingface's TRL library. A key characteristic of this model's development is its optimized training process, which was completed twice as fast due to Unsloth's efficiency.

Key Capabilities

  • Efficient Fine-tuning: Benefits from Unsloth's optimizations, enabling faster training times.
  • Gemma-2 Architecture: Leverages the capabilities of the Gemma-2 base model.
  • Compact Size: At 2.6 billion parameters, it offers a balance between performance and resource efficiency.

Good For

  • Rapid Prototyping: Ideal for projects requiring quick iteration and deployment of fine-tuned models.
  • Resource-Constrained Environments: Suitable for applications where computational resources or memory are limited.
  • Research and Development: Provides a solid base for further experimentation and fine-tuning on specific tasks, especially within the RAG (Retrieval Augmented Generation) context as implied by its name.