docs: add ikun-call to org README
Browse files
README.md
CHANGED
|
@@ -15,9 +15,9 @@ pinned: false
|
|
| 15 |
|
| 16 |
IKUN-LLM is an open-source organization dedicated to building a **complete LLM learning curriculum** β from tokenizer to deployment β using ikun meme culture as the teaching medium.
|
| 17 |
|
| 18 |
-
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](https://github.com/jingyaogong/minimind). The "2.5B" in the name stands for
|
| 19 |
|
| 20 |
-
π Try our
|
| 21 |
|
| 22 |
## Models & Data
|
| 23 |
|
|
@@ -26,9 +26,21 @@ We believe learning AI should be fun. Our flagship model **ikun-2.5B** (26M para
|
|
| 26 |
|
| 27 |
## Learning Path
|
| 28 |
|
| 29 |
-
|
| 30 |
|
| 31 |
**Fundamentals** β ikun-basics Β· ikun-tokenizer Β· ikun-pretrain Β· **ikun-2.5B** (SFT)
|
| 32 |
**Alignment** β ikun-DPO Β· ikun-GRPO Β· ikun-Reason
|
| 33 |
**Advanced** β ikun-MoE Β· ikun-Distill Β· ikun-V (multimodal)
|
| 34 |
-
**Engineering** β ikun-deploy
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
IKUN-LLM is an open-source organization dedicated to building a **complete LLM learning curriculum** β from tokenizer to deployment β using ikun meme culture as the teaching medium.
|
| 17 |
|
| 18 |
+
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](https://github.com/jingyaogong/minimind). The "2.5B" in the name stands for "two and a half years of practice" β itself a meme.
|
| 19 |
|
| 20 |
+
π Try our apps: [ikun-2.5B Chat](https://huggingface.co/spaces/IKUN-LLM/ikun-2.5B-chat) | [π ikun-call Voice Chat](https://huggingface.co/spaces/IKUN-LLM/ikun-call) | [ιΈ‘δΉη Soundboard](https://huggingface.co/spaces/IKUN-LLM/jilehe) | [Dance Simulator](https://huggingface.co/spaces/IKUN-LLM/ikun-dance) | [Emoji Gallery](https://huggingface.co/spaces/IKUN-LLM/ikun-emoji)
|
| 21 |
|
| 22 |
## Models & Data
|
| 23 |
|
|
|
|
| 26 |
|
| 27 |
## Learning Path
|
| 28 |
|
| 29 |
+
12 open-source repos covering the full LLM stack, all on [GitHub](https://github.com/ikun-llm):
|
| 30 |
|
| 31 |
**Fundamentals** β ikun-basics Β· ikun-tokenizer Β· ikun-pretrain Β· **ikun-2.5B** (SFT)
|
| 32 |
**Alignment** β ikun-DPO Β· ikun-GRPO Β· ikun-Reason
|
| 33 |
**Advanced** β ikun-MoE Β· ikun-Distill Β· ikun-V (multimodal)
|
| 34 |
+
**Engineering** β ikun-deploy Β· **[ikun-call](https://github.com/ikun-llm/ikun-call)** (real-time voice chat)
|
| 35 |
+
|
| 36 |
+
## NEW: ikun-call π
|
| 37 |
+
|
| 38 |
+
**η»ε€ε€ζη΅θ―** β Real-time voice conversation with ikun-2.5B.
|
| 39 |
+
|
| 40 |
+
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.
|
| 41 |
+
|
| 42 |
+
- Always-on listening β just talk, no button pressing
|
| 43 |
+
- Doubao-style calling UI β pure black, immersive, mobile-first
|
| 44 |
+
- 49MB model, zero API cost, runs anywhere
|
| 45 |
+
|
| 46 |
+
π [Try it live](https://huggingface.co/spaces/IKUN-LLM/ikun-call) | [GitHub](https://github.com/ikun-llm/ikun-call)
|