Llama3.1-8B-Base-Linear-Math-Code/mergekit_config.yml at main - Llama3.1-8B-Base-Linear-Math-Code - Gitea: Git with a cup of tea

Alelcv27/Llama3.1-8B-Base-Linear-Math-Code

Files

ModelHub XC 4eb9e0e1e8 初始化项目，由ModelHub XC社区提供模型

Model: Alelcv27/Llama3.1-8B-Base-Linear-Math-Code
Source: Original Platform

2026-05-11 10:39:41 +08:00

14 lines

316 B

YAML

Raw Permalink Blame History

 dtype: float16
 merge_method: linear
 modules:
   default:
     slices:
     - sources:
       - layer_range: [0, 32]
         model: Alelcv27/Llama3.1-8B-Base-Code
         parameters:
           weight: 0.6
       - layer_range: [0, 32]
         model: Alelcv27/Llama3.1-8B-Base-Math
         parameters:
           weight: 0.4