sophosympatheia's picture
Upload model weights (#1)
fadbf28 verified
|
raw
history blame
853 Bytes
metadata
base_model: []
tags:
  - mergekit
  - merge

mr-v2.0.3-miqu

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:

  • /home/llm/mergequant/models/midnight-rose-70b-v2.0.1
  • /home/llm/mergequant/models/wizard-tulu-dolphin-70b-v1.0-slerp

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /home/llm/mergequant/models/midnight-rose-70b-v2.0.1
  - model: /home/llm/mergequant/models/wizard-tulu-dolphin-70b-v1.0-slerp
merge_method: slerp
base_model: /home/llm/mergequant/models/wizard-tulu-dolphin-70b-v1.0-slerp
parameters:
  t:
    - value: [0.4, 0.6, 0.5]
dtype: float16