--- base_model: Qwen/Qwen2.5-3B-Instruct library_name: peft model_name: Globe Theatre Qwen 2.5 3B LoRA tags: - lora - peft - sft - text-generation - comedy - shakespeare - qwen2.5 - transformers - trl - creative-writing - hackathon - build-small license: apache-2.0 --- # 🎭 The Tragedy of the Group Chat: LoRA Adapter A LoRA adapter for Qwen2.5-3B-Instruct that transforms everyday modern inconveniences into short theatrical comedy scenes. This model was created for the Hugging Face Build-Small Hackathon (June 2026) as an experiment in small-model style fine-tuning. Rather than building a general-purpose assistant, the goal was to teach a relatively small (3B parameter) model a highly specific comedic voice using a compact hand-written training corpus and iterative evaluation. The project explores how much personality and structure can be taught to a local model without relying on external APIs or retrieval systems. ## What does it do? Give the model a small modern annoyance: > My neighbour's cat judged me through the window. > The bakery sold out of the exact pastry I had emotionally chosen. > The automatic lights turned off while I was still in the shower. …and it will produce a short comic scene in the style of a badly organised Elizabethan theatre company. Typical outputs include: * TITLE * DRAMATIS PERSONAE * SCENE * THOU MUST CHOOSE ## Style The intended voice combines influences from: * Shakespeare * Blackadder * Monty Python * British sitcoms * Amateur dramatic societies The goal is not historical accuracy, but readable modern dialogue with theatrical overreaction. ## Training This adapter was fine-tuned using LoRA with supervised fine-tuning (SFT) on a hand-curated dataset of approximately 240 examples. The dataset was iteratively refined over multiple training runs to improve: * structural consistency * role selection * relevance to the original grievance * comedic escalation * dialogue quality On a 10-prompt held-out manual evaluation, the fine-tuned model scored **56/80**, compared with **36/80** for the base Qwen2.5-3B-Instruct model using the same prompt and scoring rubric. ## Design principles The model was trained around a few simple ideas: * Take the grievance seriously. * Make the reaction wildly disproportionate. * Keep the cast reasonably small and situation-specific. * Let the comedy emerge from the original complaint. * Never solve the problem sensibly. ## Intended use The model works best for: * everyday annoyances * social awkwardness * household disasters * transport failures * office politics * mildly haunted appliances * inexplicably judgemental animals It is intended for entertainment and creative text generation. ## Limitations This model intentionally prioritises style over factual accuracy. Recurring characters and running jokes are expected behaviour. The model performs best on small everyday frustrations rather than major life events. ## Project structure The project consists of three related repositories: - **LoRA adapter (this repository)**: The original PEFT fine-tuning.
- **Merged model**: A standalone Transformers version of the model.
- **GGUF edition**: A quantised deployment build for llama.cpp and local inference. ## Quick start This repository contains a PEFT LoRA adapter and should be loaded on top of Qwen2.5-3B-Instruct. ## About the project The objective was not to build a general-purpose assistant, but a small theatrical comedy troupe capable of treating everyday inconveniences as matters of grave national importance. ## Training procedure This model was trained with supervised fine-tuning (SFT) using TRL and PEFT. ### Framework versions - PEFT 0.19.1 - TRL 1.6.0 - Transformers 5.10.2 - PyTorch 2.11.0+cu128 - Datasets 5.0.0 - Tokenizers 0.22.2 - ## Try the model - 🎭 [Interactive demo](https://huggingface.co/spaces/sdavies/tragedy-of-the-group-chat) ## Related repositories - [Merged model](https://huggingface.co/sdavies/globe-theatre-qwen25-3b-merged) - [GGUF edition](https://huggingface.co/sdavies/globe-theatre-qwen25-3b-gguf)