niro-preview-2409 / README.md
appvoid's picture
Upload folder using huggingface_hub
1a6436a verified
|
raw
history blame
1.2 kB
metadata
base_model:
  - trollek/danube2-1.8b-Synthia-v1.3
  - trollek/danube2-1.8b-WizardLM-Evol-V2-Unfiltered
library_name: transformers
tags:
  - mergekit
  - merge

a-really-good-gpt-x6

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:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: trollek/danube2-1.8b-WizardLM-Evol-V2-Unfiltered
        layer_range: [0, 24]
      - model: trollek/danube2-1.8b-Synthia-v1.3
        layer_range: [0, 24]
merge_method: slerp
base_model: trollek/danube2-1.8b-WizardLM-Evol-V2-Unfiltered
parameters:
  t:
    - filter: self_attn
      value: [0, 0.3, 0.5, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: float16