Hyeongwon/P19-split1-prob-6x-bs128-lr2e5-zero3-ep3

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:May 10, 2026Architecture:Transformer Warm

Hyeongwon/P19-split1-prob-6x-bs128-lr2e5-zero3-ep3 is a 4 billion parameter language model, fine-tuned from Hyeongwon/Qwen3-4B-Base using the TRL framework. This model was trained with Supervised Fine-Tuning (SFT) and features a 32768 token context length. It is designed for general text generation tasks, leveraging its base architecture and fine-tuning for improved performance.

Loading preview...

Model Overview

Hyeongwon/P19-split1-prob-6x-bs128-lr2e5-zero3-ep3 is a 4 billion parameter language model developed by Hyeongwon. It is a fine-tuned variant of the Hyeongwon/Qwen3-4B-Base model, specifically trained using the TRL (Transformer Reinforcement Learning) framework.

Key Characteristics

  • Base Model: Fine-tuned from Hyeongwon/Qwen3-4B-Base.
  • Training Method: Utilizes Supervised Fine-Tuning (SFT) as part of its training procedure.
  • Context Length: Supports a context window of 32768 tokens.
  • Frameworks: Developed with TRL (version 0.25.1), Transformers (version 4.57.3), Pytorch (version 2.9.1), Datasets (version 3.6.0), and Tokenizers (version 0.22.2).

Usage

This model is suitable for various text generation tasks. A quick start example is provided for generating responses to prompts using the transformers pipeline, demonstrating its capability in conversational or question-answering contexts.