Hyeongwon/P19-split3-prob-3x-bs64-lr2e5-zero3-ep3

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

The Hyeongwon/P19-split3-prob-3x-bs64-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 supports a 32768 token context length. It is designed for general text generation tasks, building upon its Qwen3-4B-Base foundation.

Loading preview...

Overview

Hyeongwon/P19-split3-prob-3x-bs64-lr2e5-zero3-ep3 is a 4 billion parameter language model, fine-tuned from the Hyeongwon/Qwen3-4B-Base architecture. This model leverages the Transformer Reinforcement Learning (TRL) framework for its training process, specifically employing Supervised Fine-Tuning (SFT).

Key Capabilities

  • Text Generation: Capable of generating coherent and contextually relevant text based on user prompts.
  • Base Model Enhancement: Builds upon the foundational capabilities of the Qwen3-4B-Base model, likely improving its performance on specific tasks through fine-tuning.
  • Context Length: Supports a substantial context window of 32768 tokens, allowing for processing and generating longer sequences of text.

Training Details

The model was trained using Supervised Fine-Tuning (SFT) with TRL version 0.25.1, Transformers 4.57.3, Pytorch 2.9.1, Datasets 3.6.0, and Tokenizers 0.22.2. The training procedure can be further explored via its Weights & Biases run, linked in the original README.

Use Cases

This model is suitable for various text generation applications where a 4 billion parameter model with a large context window is beneficial. It can be used for tasks such as creative writing, question answering, summarization, and conversational AI, leveraging its fine-tuned capabilities.