cookinai's picture
Update README.md
d8b5641 verified
metadata
license: cc-by-nc-4.0
library_name: transformers
tags:
  - mergekit
  - merge

OrcaHermes

OrcaHermes-Mistral-70B

This model was created by SLERP Merging 2 Miqu Models trained on 2 high preforming datsets.

Just an experiment, have not seen much miqu slerps yet.

Models Merged

The following models were included in the merge:

alicecomfy/miqu-openhermes-full

ShinojiResearch/Senku-70B-Full

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: local//path//to//Senku-70B-Full
        layer_range: [0, 80]
      - model: local//path//to//miqu-openhermes-full
        layer_range: [0, 80]
merge_method: slerp
base_model: local//path//to//Senku-70B-Full
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5 # fallback for rest of tensors
dtype: float16