xiaomenshen commited on
Commit
711b8ad
·
verified ·
1 Parent(s): d6c4dc0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -6,7 +6,7 @@ license: mit
6
 
7
  **Kimi-K25-eagle3** is an advanced and highly specialized draft model meticulously engineered to significantly accelerate the inference process of the Kimi-K25 ecosystem, leveraging the powerful **EAGLE3** framework.
8
 
9
- Architected upon the robust **Llama architecture**, this model functions as an exceptionally efficient drafter. It has undergone rigorous training on **1 million high-quality samples** sourced from the comprehensive **EagleChat** dataset. This extensive training ensures precise and strict alignment with the teacher model's distribution, thereby guaranteeing high fidelity and performance.
10
 
11
 
12
  ## Performance & Acceleration
 
6
 
7
  **Kimi-K25-eagle3** is an advanced and highly specialized draft model meticulously engineered to significantly accelerate the inference process of the Kimi-K25 ecosystem, leveraging the powerful **EAGLE3** framework.
8
 
9
+ Architected upon the robust **Llama architecture**, this model functions as an exceptionally efficient drafter. It has undergone rigorous training on **1 million high-quality samples** sourced from the comprehensive **EagleChat** dataset and some multimodal data. This extensive training ensures precise and strict alignment with the teacher model's distribution, thereby guaranteeing high fidelity and performance.
10
 
11
 
12
  ## Performance & Acceleration