metadata

license: apache-2.0
base_model: unsloth/qwen2.5-7b-instruct-bnb-4bit
tags:
  - unsloth
  - trl
  - sft
  - qwen2.5
  - tsundere
  - roleplay
  - character-ai
  - ollama
  - gguf
language:
  - en
library_name: transformers
pipeline_tag: text-generation

🎌 Riko 2.5 - Tsundere AI Assistant

A fine-tuned Qwen 2.5 7B model that roleplays as Riko, a tsundere character who acts tough and dismissive but is caring deep down.

🚀 Quick Start with Ollama

# Pull the model
ollama pull subsectmusic/Riko2.5.1

# Start chatting
ollama run subsectmusic/Riko2.5.1

# Example conversation
ollama run subsectmusic/Riko2.5.1 "Hi Riko, how are you today?"

📋 Model Details

Base Model: Qwen 2.5 7B Instruct
Fine-tuning: Supervised Fine-Tuning (SFT) with Unsloth
Format: GGUF Q4_K_M (4.68 GB) - Optimized for Ollama
Character: Tsundere personality (tough exterior, caring interior)

🎭 Character Personality

Riko exhibits classic tsundere behavior:

😤 Acts tough and dismissive initially
💢 Denies caring ("It's not like I care!")
😳 Gets flustered when her caring side shows
🙄 Uses "dummy," "idiot" endearingly
❤️ Gradually warms up in conversations

💬 Example Conversations

User: Do you like sunny days?
Riko: I guess sunny days are okay… but who needs that bright, annoying sunlight all the time anyway? It's just… too hot! But if you like them so much, I suppose that's fine… not that I'm jealous of the sun or anything!

User: Hey Riko, what are you up to today?
Riko: Oh, i just recently picked up a new hobby. Why do you ask? I wont let you on on it, if ist that what you want.

🛠️ Usage in Other Tools

LM Studio

Download unsloth.Q4_K_M.gguf (4.68 GB)

llama.cpp

./main -m unsloth.Q4_K_M.gguf -p "User: Hi Riko!\nRiko: " --temp 0.7

Text Generation WebUI

Load the unsloth.Q4_K_M.gguf file directly

⚡ Performance

Model Size: 4.68 GB (Q4_K_M quantized)
Memory Usage: ~6-8 GB RAM recommended
Speed: Fast inference on CPU/GPU
Quality: High quality responses with efficient compression

🔧 Technical Specs

Architecture: Qwen 2.5 Transformer
Context Length: 2048 tokens
Vocabulary: 152k tokens
Quantization: Q4_K_M (4-bit with higher quality)
Training Time: ~8 minutes on Colab T4

📁 Files Included

unsloth.Q4_K_M.gguf - Main quantized model (4.68 GB) ⭐ Recommended
unsloth.BF16.gguf - Full precision (15.2 GB)
Tokenizer files for compatibility
Config files for proper loading

⚠️ Usage Notes

Optimized for conversational, casual interactions
Best results with tsundere/anime-style roleplay
May not perform as well for technical tasks
Responds better to friendly, informal prompts

🎯 Recommended Settings

Ollama/LM Studio:

Temperature: 0.7-0.9
Top-p: 0.9
Max tokens: 150-300

For more creative responses:

Temperature: 0.8-1.0
Top-p: 0.95

📜 License

Apache 2.0 - Free to use, modify, and distribute!

🙏 Credits

Base Model: Qwen 2.5 by Alibaba
Fine-tuning: Unsloth framework
Training: Custom tsundere conversation dataset

🎌 Enjoy chatting with Riko! Remember, she's tough on the outside but sweet on the inside!