Hyeongwon/P19-split1-prob-3x-bs64-lr2e5-zero3-ep3

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:May 9, 2026Architecture:Transformer Warm

Hyeongwon/P19-split1-prob-3x-bs64-lr2e5-zero3-ep3 is a 4 billion parameter language model fine-tuned from Hyeongwon/Qwen3-4B-Base. This model was trained using the TRL framework with a supervised fine-tuning (SFT) approach. It is designed for general text generation tasks, building upon the capabilities of its Qwen3-4B-Base foundation.

Loading preview...

Overview

This model, named Hyeongwon/P19-split1-prob-3x-bs64-lr2e5-zero3-ep3, is a 4 billion parameter language model. It is a fine-tuned variant of the Hyeongwon/Qwen3-4B-Base model, indicating its foundation in the Qwen3 architecture. The fine-tuning process utilized the TRL (Transformer Reinforcement Learning) framework, specifically employing a Supervised Fine-Tuning (SFT) methodology.

Key Capabilities

  • Text Generation: Capable of generating coherent and contextually relevant text based on user prompts.
  • Fine-tuned Performance: Benefits from additional training on top of a robust base model, potentially enhancing its performance for specific applications.
  • TRL Framework: Developed using the TRL library, which is designed for transformer reinforcement learning, suggesting potential for further adaptation or specialized tasks.

Training Details

The model's training involved a supervised fine-tuning (SFT) approach. The development environment included specific versions of key frameworks:

  • TRL: 0.25.1
  • Transformers: 4.57.3
  • Pytorch: 2.9.1
  • Datasets: 3.6.0
  • Tokenizers: 0.22.2

Good For

  • Developers looking for a fine-tuned 4B parameter model based on Qwen3 for various text generation tasks.
  • Experimentation with models trained using the TRL framework and SFT methods.
  • Applications requiring a moderately sized language model with a 32768 token context length.