Dnoya10/dicoding_genAI_expert_collab_eks1

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 5, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The Dnoya10/dicoding_genAI_expert_collab_eks1 is a 1.5 billion parameter Qwen2-based instruction-tuned causal language model developed by Dnoya10. This model was finetuned using Unsloth and Huggingface's TRL library, resulting in a 2x faster training process. It is designed for general instruction-following tasks, leveraging its efficient training methodology.

Loading preview...

Model Overview

Dnoya10/dicoding_genAI_expert_collab_eks1 is a 1.5 billion parameter instruction-tuned language model based on the Qwen2 architecture. Developed by Dnoya10, this model was finetuned from unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit.

Key Characteristics

  • Efficient Training: This model was trained significantly faster, achieving a 2x speedup, by utilizing Unsloth and Huggingface's TRL library. This efficiency in training can translate to more agile development and iteration cycles.
  • Qwen2 Foundation: Built upon the robust Qwen2 architecture, it inherits strong general language understanding and generation capabilities.
  • Instruction-Tuned: The model is instruction-tuned, making it suitable for a variety of prompt-based tasks where it needs to follow specific instructions.

Use Cases

This model is well-suited for applications requiring a compact yet capable instruction-following LLM, especially where training efficiency is a priority. Its 1.5 billion parameters and 32768 token context length make it a strong candidate for:

  • General text generation based on instructions.
  • Chatbot development.
  • Summarization and question-answering tasks.
  • Applications where resource efficiency and faster deployment are beneficial.

Finetunes
1 models