CultriX/Qwen2.5-14B-ReasoningMerge
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: CultriX/Qwen2.5-14B-ReasoningMerge
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-21 16:10:19 +08:00
commit 82aec94864
17 changed files with 151806 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
mergekit_config.yml Normal file
View File

@@ -0,0 +1,16 @@
base_model: Sakalti/Saka-14B
merge_method: slerp
dtype: bfloat16
parameters:
t:
- filter: self_attn
value: 0.4 # Favor RDson/WomboCombo for self-attention
- filter: mlp
value: 0.7 # Favor Sakalti/Saka-14B for MLP layers
- value: 0.5
models:
- model: Sakalti/Saka-14B
- model: RDson/WomboCombo-R1-Coder-14B-Preview
tokenizer_source: Sakalti/Saka-14B
chat_template: chatml
name: reasoning_blend