mergekit icon indicating copy to clipboard operation
mergekit copied to clipboard

Condense a models layers.

Open DewEfresh opened this issue 7 months ago • 0 comments

I am trying to condense a model by 1/4. I want to merge the 4 layer over the previous 3 layers, When i try this i get 0 layers on the merged model. Here is a sample of the config.yaml. I'm using the LazyMergekit colab to merge the model. slices:

  • sources:

    First part: merge layer 0 with layer 3

    • model: DewEfresh/neo_7b layer_range: [0, 0]
    • model: DewEfresh/neo_7b layer_range: [3, 3]
  • sources:

    Second part: merge layer 1 with layer 3

    • model: DewEfresh/neo_7b layer_range: [1, 1]
    • model: DewEfresh/neo_7b layer_range: [3, 3]
  • sources:

    Third part: merge layer 2 with layer 3

    • model: DewEfresh/neo_7b layer_range: [2, 2]
    • model: DewEfresh/neo_7b layer_range: [3, 3]

heres the full config https://huggingface.co/DewEfresh/Neo_7b-merge14/blob/main/mergekit_config.yml. Any help would be appreciated.

DewEfresh avatar Jul 01 '24 21:07 DewEfresh