xiaomenshen commited on
Commit
ff8e7cd
·
verified ·
1 Parent(s): 2bbfea5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -7,7 +7,7 @@ Thanks to the **SpecForge** framework for their foundational contributions. Stay
7
 
8
  ## Model Overview
9
 
10
- **Kimi-K26-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.
11
 
12
  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 **open-perfectblend** 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.
13
 
 
7
 
8
  ## Model Overview
9
 
10
+ **Kimi-K26-eagle3** is an advanced and highly specialized draft model meticulously engineered to significantly accelerate the inference process of the Kimi-K26 ecosystem, leveraging the powerful **EAGLE3** framework.
11
 
12
  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 **open-perfectblend** 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.
13