kargeor/Qwen2.5-32B-Cyberpunk-Storyteller-v2

Hugging Face
TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kPublished:Mar 16, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The kargeor/Qwen2.5-32B-Cyberpunk-Storyteller-v2 is a 32.8 billion parameter Qwen2.5-based language model, fine-tuned by kargeor for cyberpunk storytelling. This model was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. It specializes in generating narrative content within the cyberpunk genre, leveraging its large parameter count and specific fine-tuning for detailed and thematic outputs.

Loading preview...

Model Overview

The kargeor/Qwen2.5-32B-Cyberpunk-Storyteller-v2 is a 32.8 billion parameter language model, fine-tuned from the huihui-ai/Qwen2.5-32B-Instruct-abliterated base model. Developed by kargeor, this model is specifically optimized for generating content within the cyberpunk genre.

Key Capabilities

  • Cyberpunk Storytelling: The primary focus of this model is to generate narratives, descriptions, and dialogues consistent with the cyberpunk aesthetic and themes.
  • Efficient Fine-tuning: The model was fine-tuned using Unsloth and Huggingface's TRL library, which allowed for a 2x faster training process.
  • Qwen2.5 Architecture: Built upon the Qwen2.5 architecture, it benefits from the foundational capabilities of this large language model family.

Good For

  • Creative Writing: Ideal for authors, game developers, or enthusiasts looking to generate cyberpunk-themed stories, character backstories, or world-building elements.
  • Content Generation: Useful for creating descriptive text, dialogue, or plot points for cyberpunk-related projects.
  • Experimentation with Efficient Fine-tuning: Demonstrates the application of Unsloth for accelerating the fine-tuning of large models.