waddie/mini-2.0
waddie/mini-2.0 is a 7.6 billion parameter language model developed by Edward Fazackerley, fine-tuned from Qwen2.5-7B-Instruct with a 32768 token context length. It is specifically designed to mimic informal, casual, and technical human conversation, adopting a "random guy" persona with lowercase-heavy and slightly secretive slang. Its primary use case is for Discord bots or roleplay scenarios requiring highly human-like, informal interaction rather than a formal AI assistant.
Loading preview...
CloudWaddie Mini 2.0 Overview
waddie/mini-2.0 is a 7.6 billion parameter language model developed by Edward Fazackerley, fine-tuned from Qwen2.5-7B-Instruct. Unlike typical helpful and formal AI assistants, this model is uniquely designed to adopt a "random guy" persona, mimicking the specific conversational rhythm, slang, and technical jargon of a human. It was trained on 10,000 Discord conversations from an AI Leaks community to capture a casual, lowercase-heavy, and slightly secretive "insider" vibe.
Key Capabilities
- Informal Human-like Interaction: Excels at generating responses with casual language, slang, and technical jargon.
- Unique Persona: Adopts a "random guy" persona, characterized by lowercase-only text and a secretive tone.
- Context Length: Supports a substantial context window of 32,768 tokens.
Good for
- Discord Bots: Ideal for creating bots that require a highly informal, human-like conversational style.
- Roleplay Scenarios: Suitable for applications where a casual, non-robotic interaction is preferred.
- Specific Conversational Mimicry: Best for use cases needing to replicate a very particular, insider-like communication style.