Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks
Paper
•
2312.06795
•
Published
•
1
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Breadcrumbs with TIES merge method using Cran-May/tempemotacilla-miscii0218-0302 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
merge_method: breadcrumbs_ties
base_model: Cran-May/tempemotacilla-miscii0218-0302
tokenizer_source: Cran-May/tempemotacilla-miscii0218-0302
name: merge_model_20250308_2
models:
- model: Cran-May/tempemotacilla-miscii0218-0302
parameters:
weight: 1.0
- model: Cran-May/tempemotacilla-lix14Bv0.1-0308
parameters:
weight: 0.75
dtype: bfloat16
Totally Free + Zero Barriers + No Login Required