icedsoylatte/wz-qwen25-3b-open-roleplay-sft-v2
TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 1, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold
The icedsoylatte/wz-qwen25-3b-open-roleplay-sft-v2 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 open-ended roleplay tasks. It was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning.
Loading preview...
Model Overview
The icedsoylatte/wz-qwen25-3b-open-roleplay-sft-v2 is a 3.1 billion parameter language model developed by icedsoylatte. It is a fine-tuned variant of the Qwen2.5 architecture, specifically building upon the unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit model.
Key Characteristics
- Base Model: Qwen2.5-3B-Instruct, known for its strong performance in its size class.
- Fine-tuning: The model has undergone supervised fine-tuning (SFT) with a focus on open-ended roleplay scenarios.
- Training Efficiency: Fine-tuning was conducted using Unsloth and Huggingface's TRL library, which facilitated a 2x faster training process.
Use Cases
This model is particularly well-suited for applications requiring:
- Roleplay Generation: Creating dynamic and engaging character interactions.
- Creative Storytelling: Generating narrative content with distinct character voices.
- Interactive AI: Developing chatbots or virtual assistants capable of maintaining consistent personas in conversational settings.