Hyeongwon/P2-split2_independent_mask_Qwen3-4B-Base_0425-bs64-epoch3

TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Apr 25, 2026Architecture:Transformer Cold

Hyeongwon/P2-split2_independent_mask_Qwen3-4B-Base_0425-bs64-epoch3 is a 4 billion parameter language model developed by Hyeongwon, fine-tuned from the Qwen3-4B-Base architecture. This model was trained using Supervised Fine-Tuning (SFT) with the TRL framework. It is designed for general text generation tasks, building upon its base model's capabilities.

Loading preview...

Overview

This model, P2-split2_independent_mask_Qwen3-4B-Base_0425-bs64-epoch3, 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 Supervised Fine-Tuning (SFT) with the TRL framework (version 0.25.1).

Key Capabilities

  • Text Generation: Capable of generating human-like text based on given prompts, as demonstrated by the quick start example for conversational responses.
  • Fine-tuned Performance: Benefits from additional SFT training, which typically enhances performance on specific tasks or improves adherence to instructions compared to its base model.

Training Details

  • Base Model: Fine-tuned from Hyeongwon/Qwen3-4B-Base.
  • Training Method: Supervised Fine-Tuning (SFT).
  • Frameworks Used: TRL (0.25.1), Transformers (4.57.3), Pytorch (2.6.0), Datasets (3.6.0), Tokenizers (0.22.2).
  • Monitoring: Training progress was monitored using Weights & Biases.

Usage

This model can be readily used for text generation tasks via the Hugging Face pipeline API, as shown in the provided quick start example. It is suitable for applications requiring conversational AI or general-purpose text completion.