RicAIEng/Llama-3-Tugas-Dicoding

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Sep 3, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Featherless Exclusive Cold

RicAIEng/Llama-3-Tugas-Dicoding is an 8 billion parameter Llama-3 based causal language model developed by RicAIEng. This model was finetuned using Unsloth and Huggingface's TRL library, enabling faster training. It is designed for general language tasks, leveraging the Llama-3 architecture for robust performance.

Loading preview...

Model Overview

RicAIEng/Llama-3-Tugas-Dicoding is an 8 billion parameter language model developed by RicAIEng. It is a finetuned variant of the Llama-3 architecture, specifically optimized for training efficiency. The model leverages the Unsloth library, which facilitates 2x faster training, in conjunction with Huggingface's TRL library.

Key Characteristics

  • Base Model: Finetuned from unsloth/llama-3-8b-bnb-4bit.
  • Training Efficiency: Utilizes Unsloth for accelerated training, making it a practical choice for developers seeking faster iteration cycles.
  • Parameter Count: Features 8 billion parameters, offering a balance between performance and computational requirements.
  • Context Length: Supports an 8192-token context window, suitable for processing moderately long inputs.

Potential Use Cases

This model is well-suited for applications where the Llama-3 8B architecture is appropriate, with an emphasis on scenarios benefiting from efficient finetuning. It can be applied to various natural language processing tasks, including:

  • Text generation and completion.
  • Instruction following.
  • Summarization and question answering.
  • Rapid prototyping and experimentation due to its optimized training process.