Hugging Face's logo

ddh0
/
MiquSuperdark-70B-v1

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
MiquSuperdark-70B-v1 / README.md
ddh0's picture
ddh0
Create README.md
3e63d0d verified
preview code
|
raw
history blame
No virus
2.03 kB
metadata
base_model:
  - sophosympatheia/Midnight-Miqu-70B-v1.5
  - NeverSleep/MiquMaid-v3-70B
  - maywell/miqu-evil-dpo
  - 152334H/miqu-1-70b-sf
library_name: transformers
tags:
  - mergekit
  - merge
license: other

MiquSuperdark-70B-v1

MiquSuperdark-70B-v1 is a merge of three of the most popular Miqu-derived models, along with Miqu itself. The goal of the merge is to create an strong, well-rounded chat model that picks up desirable traits from its constituent models without sacrificing intelligence.

This is a DARE Linear merge with the following composition:

DARE Linear was chosen as the merge method based on this HF discussion, in which the creator of Midnight-Miqu says "in my own testing I consistently got the best results from using a dare_linear merge when working with miqu models".

Merge Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_linear
base_model: /home/dylan/Documents/AI/merge/miqu-1-70b-sf
models:
  - model: /media/dylan/SanDisk/LLMs/Midnight-Miqu-70B-v1.5
    parameters:
      weight: 0.4
  - model: /home/dylan/Documents/AI/merge/miqu-1-70b-sf
    parameters:
      weight: 0.2
  - model: /media/dylan/SanDisk/LLMs/miqu-evil-dpo/
    parameters:
      weight: 0.2
  - model: /home/dylan/Documents/AI/merge/MiquMaid-v3-70B
    parameters:
      weight: 0.2
dtype: float16
tokenizer_source: model:/home/dylan/Documents/AI/merge/miqu-1-70b-sf

The tokenizer is copied from the base model 152334H/miqu-1-70b-sf.