merge_all

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Linear merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: sraj/CMB_Acad_LRDat0.1mlm
    parameters:
      weight: 1.0
  - model: sraj/CMB_FWEdu_V3_LRDat0.1mlm
    parameters:
      weight: 1.0
  - model: sraj/CMB_SYN_LRDat0.1mlm
    parameters:
      weight: 1.0
merge_method: linear
parameters:
  normalize: true
dtype: bfloat16

Downloads last month: 33

Safetensors

Model size

0.1B params

Tensor type

BF16

Model tree for sraj/Merge_SOUP_at0.1mlm

sraj/CMB_Acad_LRDat0.1mlm

sraj/CMB_FWEdu_V3_LRDat0.1mlm

sraj/CMB_SYN_LRDat0.1mlm

Merge model

this model

Paper for sraj/Merge_SOUP_at0.1mlm

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Paper • 2203.05482 • Published Mar 10, 2022 • 10