Exponenta-Alpha-7B / README.md
Inv's picture
Update README.md
256792d verified
metadata
base_model:
  - Inv/Konstanta-V4-Alpha-7B
library_name: transformers
tags:
  - mergekit
  - merge
license: apache-2.0

Exponenta-Alpha-7B

This is a merge of pre-trained language models created using mergekit. I've used exponential function with base of 2 for this one.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


slices:
  - sources:
    - model: Inv/Konstanta-V4-Alpha-7B
      layer_range: [0,32]
    - model: /content/drive/MyDrive/InfinityRP-Split
      layer_range: [0,32]
merge_method: slerp
base_model: Inv/Konstanta-V4-Alpha-7B
parameters:
  t:
    - filter: self_attn
      value: [0.0002, 0.0004, 0.0008, 0.0016, 0.0032, 0.0064, 0.0128, 0.0256, 0.0512, 0.1024, 0.2048, 0.4096, 0.8192]
    - filter: mlp
      value: [0.8192, 0.4096, 0.2048, 0.1024, 0.0512, 0.0256, 0.0128, 0.0064, 0.0032, 0.0016, 0.0008, 0.0004, 0.0002]
    - value: 0.5
dtype: bfloat16