icedsoylatte/wz-qwen25-3b-chai-roleplay-sft-v4

TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jun 30, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The icedsoylatte/wz-qwen25-3b-chai-roleplay-sft-v4 is a 3.1 billion parameter Qwen2.5-based causal language model developed by icedsoylatte. Fine-tuned from unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit, this model is optimized for roleplay and conversational tasks. It leverages Unsloth and Huggingface's TRL library for efficient training, offering a specialized solution for interactive narrative generation.

Loading preview...

Model Overview

The icedsoylatte/wz-qwen25-3b-chai-roleplay-sft-v4 is a 3.1 billion parameter language model, developed by icedsoylatte. It is built upon the Qwen2.5 architecture and has been specifically fine-tuned for roleplay and conversational applications. The model was trained using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.

Key Characteristics

  • Base Model: Finetuned from unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit.
  • Parameter Count: 3.1 billion parameters, offering a balance between performance and computational efficiency.
  • Training Efficiency: Utilizes Unsloth for accelerated training, making it a practical choice for specialized applications.

Ideal Use Cases

This model is particularly well-suited for scenarios requiring:

  • Roleplay Generation: Creating dynamic and engaging character interactions.
  • Interactive Storytelling: Developing narrative experiences where the model takes on specific personas.
  • Conversational AI: Applications focused on generating contextually relevant and character-driven dialogue.