README.md

metadata

title: README
emoji: 🏀
colorFrom: yellow
colorTo: red
sdk: static
pinned: false

Welcome to IKUN-LLM 🏀

IKUN-LLM is an open-source organization dedicated to building a complete LLM learning curriculum — from tokenizer to deployment — using ikun meme culture as the teaching medium.

We believe learning AI should be fun. Our flagship model ikun-2.5B (26M params) is a Chinese meme-culture dialogue model fine-tuned on MiniMind. The "2.5B" in the name stands for "two and a half years of practice" — itself a meme.

👉 Try our apps: ikun-2.5B Chat | 📞 ikun-call Voice Chat | 鸡乐盒 Soundboard | Dance Simulator | Emoji Gallery

Models & Data

• ikun-2.5B — 26M parameter Chinese dialogue model (LoRA fine-tuned, Apache 2.0)
• CXK_IKUN_Dataset — ~200 meme-culture SFT dialogue samples

Learning Path

12 open-source repos covering the full LLM stack, all on GitHub:

Fundamentals → ikun-basics · ikun-tokenizer · ikun-pretrain · ikun-2.5B (SFT) Alignment → ikun-DPO · ikun-GRPO · ikun-Reason Advanced → ikun-MoE · ikun-Distill · ikun-V (multimodal) Engineering → ikun-deploy · ikun-call (real-time voice chat)

NEW: ikun-call 📞

给坤坤打电话 — Real-time voice conversation with ikun-2.5B.

The 26M model runs inference in <100ms. Combined with browser speech recognition and edge-tts, you get a phone-call-like experience with an AI that speaks ikun memes.

• Always-on listening — just talk, no button pressing
• Doubao-style calling UI — pure black, immersive, mobile-first
• 49MB model, zero API cost, runs anywhere

👉 Try it live | GitHub