Resolving Interference When Merging Models
Paper
• 2306.01708 • Published
• 17
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using HuggingFaceH4/zephyr-7b-alpha as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: Sakalti/magro-7B
parameters:
weight: 1
density: 1
merge_method: ties
base_model: HuggingFaceH4/zephyr-7b-alpha
parameters:
weight: 1
density: 1
normalize: true
int8_mask: true
dtype: bfloat16