Dnoya10/dicoding_genAI_expert_adv_eks2

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 13, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

Dnoya10/dicoding_genAI_expert_adv_eks2 is a 1.5 billion parameter Qwen2.5-based instruction-tuned causal language model developed by Dnoya10. This model was finetuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. With a 32768 token context length, it is optimized for efficient performance in generative AI applications.

Loading preview...

Model Overview

Dnoya10/dicoding_genAI_expert_adv_eks2 is an instruction-tuned language model based on the Qwen2.5 architecture, featuring 1.5 billion parameters. Developed by Dnoya10, this model was specifically finetuned from unsloth/qwen2.5-1.5b-instruct-unsloth-bnb-4bit.

Key Characteristics

  • Efficient Training: This model leverages Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process compared to standard methods.
  • Parameter Count: With 1.5 billion parameters, it offers a balance between performance and computational efficiency.
  • Context Length: The model supports a substantial context window of 32768 tokens, allowing for processing longer inputs and generating more coherent, extended outputs.

Potential Use Cases

This model is suitable for various generative AI tasks where a compact yet capable instruction-tuned model is beneficial. Its efficient training methodology suggests it could be a good candidate for applications requiring rapid iteration or deployment on resource-constrained environments. Developers looking for a Qwen2.5-based model with optimized training will find this particularly useful for general instruction-following tasks.

Finetunes
1 models