DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
Paper
• 2406.11617 • Published
• 10
This is a merge of pre-trained language models created using mergekit.
This model was merged using the DELLA merge method using YOYO-AI/Qwen2.5-14B-YOYO-V5 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: qihoo360/Light-R1-14B-DS
parameters:
density: 1
weight: 1
lambda: 0.9
merge_method: della
base_model: YOYO-AI/Qwen2.5-14B-YOYO-V5
parameters:
density: 1
weight: 1
lambda: 0.9
normalize: true
int8_mask: true
dtype: float16
tokenizer_source: base