Hugging Face's logo

ND911
/
Eclectic-Maid-10B-gguf

Transformers
GGUF
mergekit
Merge
Not-For-All-Audiences
Inference Endpoints
Model card Files Community
Eclectic-Maid-10B-gguf / README.md
ND911's picture
ND911
Create README.md
1f6cd52 verified
preview code
|
raw
history blame contribute delete
No virus
3.21 kB
metadata
base_model: []
library_name: transformers
tags:
  - mergekit
  - merge
  - not-for-all-audiences

Eclectic-Maid-10B

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

Merge Details

A reborn Maid model with many models and several merges. Seems to work well with Alpac Roleplay, ChatML, noromaid settings in Silly Tavern

Merge Method

This model was merged using the DARE TIES merge method using Eclectic-Maid-10B-p1 as a base.

Models Merged

Many

Configuration

The following YAML configuration was used to produce this model:

models: 
  - model: Eclectic-Maid-10B-p1
    # no parameters necessary for base model
  - model: Eclectic-Maid-10B-p2
    parameters:
      weight: 0.50
      density: 0.5
  - model: Eclectic-Maid-10B-p2
    parameters:
      weight: 0.50
      density: 0.5
merge_method: dare_ties
base_model: Eclectic-Maid-10B-p1
parameters:
  int8_mask: true
dtype: bfloat16
name: Eclectic Maid

name: Maid-Reborn
models: 
  - model: mistralai/Mistral-7B-Instruct-v0.2
    # no parameters necessary for base model
  - model: xDAN-AI/xDAN-L1-Chat-RL-v1
    parameters:
      weight: 0.4
      density: 0.8
  - model: Undi95/BigL-7B
    parameters:
      weight: 0.3
      density: 0.8
  - model: SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE
    parameters:
      weight: 0.2
      density: 0.4
  - model: NeverSleep/Noromaid-7B-0.4-DPO
    parameters:
      weight: 0.2
      density: 0.4
  - model: NSFW_DPO_Noromaid-7B-v2
    parameters:
      weight: 0.2
      density: 0.4
merge_method: dare_ties
base_model: mistralai/Mistral-7B-Instruct-v0.2
parameters:
  int8_mask: true
dtype: bfloat16

models: 
  - model: Maid-Reborn-7B
    # no parameters necessary for base model
  - model: localfultonextractor/Erosumika-7B-v2
    parameters:
      weight: 0.4
      density: 0.5
  - model: Undi95/BigL-7B
    parameters:
      weight: 0.3
      density: 0.5
  - model: Maid-Reborn-7B
    parameters:
      weight: 0.2
      density: 0.4
  - model: openchat_openchat-3.5-1210
    parameters:
      weight: 0.2
      density: 0.3
  - model: Nexusflow/Starling-LM-7B-beta
    parameters:
      weight: 0.2
      density: 0.3
merge_method: dare_ties
base_model: Maid-Reborn-7B
parameters:
  int8_mask: true
dtype: bfloat16

models:
  - model: Maid-Reborn-10B-p1
    # no parameters necessary for base model
  - model: Maid-Reborn-10B-p2
    parameters:
      weight: 0.30
      density: 0.5
  - model: Maid-Reborn-10B-p2
    parameters:
      weight: 0.30
      density: 0.5
merge_method: dare_ties
base_model: Maid-Reborn-10B-p1
parameters:
  int8_mask: true
dtype: bfloat16
name: Eclectic Maid

models: 
  - model: Maid-Reborn-10B-p2
    # no parameters necessary for base model
  - model: Maid-Reborn-10B-p1
    parameters:
      weight: 0.30
      density: 0.5
  - model: Maid-Reborn-10B-p1
    parameters:
      weight: 0.30
      density: 0.5
merge_method: dare_ties
base_model: Maid-Reborn-10B-p2
parameters:
  int8_mask: true
dtype: bfloat16
name: Eclectic Maid