Qwen3+PDAPT+SLERP
Collection
Experiments conducted for the LREC paper () • 8 items • Updated
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: /home/mrim/manniona/partages/models/hf-dl/Qwen/Qwen3-0.6B-Base
layer_range: [0, 28]
- model: /home/mrim/manniona/partages/models/share/Qwen3-0.6B-Base-PARTAGES-v2-2160
layer_range: [0, 28]
merge_method: slerp
base_model: /home/mrim/manniona/partages/models/hf-dl/Qwen/Qwen3-0.6B-Base
parameters:
t:
- value: 0.5
dtype: bfloat16