trained_models
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Breadcrumbs with TIES merge method using vera6/affine-5GmvsbydEDvdhHy6w8JHMCorYyJPiAnvzHWaa8Aj6iTdzzns as a base.
Models Merged
The following models were included in the merge:
- OronoCris/affine-83-5ETkv1LSG1sMVBma1oPQUUKPkzmLDHQN7zwf8sWqCQEps3yR
- DuWenJing/affine-model-5CrVf11voFhxLs2nM7LBVUKPfD4gNwYugag4Dmwe8JM423RC
Configuration
The following YAML configuration was used to produce this model:
merge_method: breadcrumbs_ties
base_model: vera6/affine-5GmvsbydEDvdhHy6w8JHMCorYyJPiAnvzHWaa8Aj6iTdzzns
models:
- model: DuWenJing/affine-model-5CrVf11voFhxLs2nM7LBVUKPfD4gNwYugag4Dmwe8JM423RC
parameters:
density: 0.95
weight: 0.7 # Increased weight for better performance
- model: OronoCris/affine-83-5ETkv1LSG1sMVBma1oPQUUKPkzmLDHQN7zwf8sWqCQEps3yR
parameters:
density: 0.8
weight: 0.3 # Decreased weight for lower performance
parameters:
density: 0.92
gamma: 0.02
dtype: bfloat16