Dnoya10/dicoding_genAI_expert_collab_grpo_4

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_collab_grpo_4 is a 1.5 billion parameter Qwen2 model, developed by Dnoya10, with a 32768 token context length. This model was fine-tuned using Unsloth and Huggingface's TRL library, enabling 2x faster training. It is designed for general language tasks, leveraging its efficient training methodology for practical applications.

Loading preview...

Overview

Dnoya10/dicoding_genAI_expert_collab_grpo_4 is a 1.5 billion parameter Qwen2 model, fine-tuned by Dnoya10. It builds upon the base model Dnoya10/dicoding_genAI_expert_collab_eks1 and features a substantial context length of 32768 tokens, allowing it to process extensive inputs and generate coherent, long-form responses. The model's development prioritized efficiency, utilizing the Unsloth library in conjunction with Huggingface's TRL for training, which reportedly accelerated the fine-tuning process by two times.

Key Capabilities

  • Efficient Training: Leverages Unsloth and Huggingface's TRL for significantly faster fine-tuning.
  • Extended Context: Supports a 32768 token context window, suitable for tasks requiring deep understanding of long texts.
  • Qwen2 Architecture: Benefits from the robust and versatile Qwen2 base model architecture.

Good For

  • Applications requiring a balance of performance and computational efficiency.
  • Tasks that benefit from processing and generating long sequences of text.
  • Developers looking for a model fine-tuned with optimized training techniques.