Update README.md

README.md

@@ -1,3 +1,48 @@
----
-license: mit
----
+---
+license: mit
+---
+
+## Model Overview
+
+**Kimi-K2-Instruct-eagle3** is a specialized draft model designed to accelerate the inference of the Kimi-K2-Instruct ecosystem using the **EAGLE3 (Extrapolation Algorithm for Greater Language-model Efficiency)** framework.
+
+Built upon the **Llama architecture**, this model acts as a highly efficient drafter. It has been trained on **1.4 million high-quality samples** from the **Open-PerfectBlend** dataset, ensuring strict alignment with the teacher model's distribution.
+
+This model serves as a general-purpose English instruction follower with strong capabilities in:
+* **Conversation**
+* **Mathematical Reasoning**
+* **Code Generation**
+
+## Performance & Acceleration
+
+The core value of this EAGLE model is its ability to predict multiple future tokens that are subsequently verified by the base model. High acceptance lengths indicate significant latency reduction.
+
+**Average Token Acceptance Lengths (MLA):**
+
+| Benchmark | Average Acceptance Length |
+| :--- | :--- |
+| **HumanEval** (Code) | **3.372** |
+| **GSM8K** (Math) | **3.165** |
+| **Math500** (Complex Math) | **3.490** |
+
+These metrics demonstrate robust acceleration performance across diverse and complex domains.
+
+![1](https://hackmd.io/_uploads/ryP6cBLXbg.png)
+![2](https://hackmd.io/_uploads/S1Da5BLmbl.png)
+![3](https://hackmd.io/_uploads/S1v65HIm-e.png)
+
+
+## Training Data
+
+The model was trained on **1.4 million samples** sourced from the **Open-PerfectBlend** dataset. The data selection prioritizes high-quality instruction-following scenarios to maximize the draft model's predictive accuracy relative to the base model.
+
+## Citation
+
+If you use this model in your research or application, please cite the following:
+
+```bibtex
+@misc{kimik2eagle3,
+  title={Kimi-K2-Instruct-eagle3: Accelerating Instruction Following with EAGLE},
+  author={Ant AQ Team},
+  year={2025},
+}