Dnoya10/dicoding_genAI_adv_collab_grpo_3

TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 17, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

Dnoya10/dicoding_genAI_adv_collab_grpo_3 is a 1.5 billion parameter Qwen2 model developed by Dnoya10, fine-tuned from Dnoya10/dicoding_genAI_expert_collab_eks2. This model was trained using Unsloth and Huggingface's TRL library, achieving a 2x speed improvement during its training process. It is designed for general language tasks, leveraging its efficient fine-tuning for practical applications.

Loading preview...

Model Overview

Dnoya10/dicoding_genAI_adv_collab_grpo_3 is a 1.5 billion parameter Qwen2 language model, developed by Dnoya10. It is a fine-tuned version of the Dnoya10/dicoding_genAI_expert_collab_eks2 model, optimized for performance and efficiency.

Key Characteristics

  • Architecture: Qwen2
  • Parameters: 1.5 billion
  • Context Length: 32768 tokens
  • Training Efficiency: Fine-tuned with Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
  • License: Apache-2.0, allowing for broad use and distribution.

Good For

  • Applications requiring a moderately sized language model with efficient training origins.
  • General natural language processing tasks where the Qwen2 architecture is suitable.
  • Developers looking for a model fine-tuned with performance-enhancing tools like Unsloth.