Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,8 @@ license: mit
|
|
| 6 |
|
| 7 |
**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.
|
| 8 |
|
|
|
|
|
|
|
| 9 |
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.
|
| 10 |
|
| 11 |
This model serves as a general-purpose English instruction follower with strong capabilities in:
|
|
|
|
| 6 |
|
| 7 |
**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.
|
| 8 |
|
| 9 |
+
Kimi-K2-Instruct with EAGLE3 achieves up to **1.8× peak throughput** versus the base model, accelerating generation across all 7 benchmarks—from +24% on MT-Bench to +80% on Math500 (configured with bs=8, steps=3, topk=1, num_draft_tokens=4).
|
| 10 |
+
|
| 11 |
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.
|
| 12 |
|
| 13 |
This model serves as a general-purpose English instruction follower with strong capabilities in:
|