Foredoomed-9B / README.md
digitous's picture
Upload 8 files
4358bd7 verified
|
raw
history blame
No virus
1.11 kB
metadata
base_model: []
library_name: transformers
tags:
  - mergekit
  - merge

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

  • D:\LLMs_downloads_Mistral__Eroplasm_Project_esperos
  • D:\LLMs_downloads_Mistral__Eroplasm_Project_casper

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: D:\LLMs\_downloads\_Mistral\__Eroplasm_Project\_esperos
        layer_range: [0, 44]
      - model: D:\LLMs\_downloads\_Mistral\__Eroplasm_Project\_casper
        layer_range: [0, 44]
merge_method: slerp
tokenizer_source: base
base_model: D:\LLMs\_downloads\_Mistral\__Eroplasm_Project\_esperos
parameters:
  embed_slerp: true
  t:
    - filter: self_attn
      value: [1, 0.5, 0.7, 0.3, 0]
    - filter: mlp
      value: [0, 0.5, 0.3, 0.7, 1]
    - value: 0.5 # fallback for rest of tensors
dtype: float32