Eclectic-Maid-10B-v2
This model is much better over original model, I believe. The recipes are not exact below but at least you get an idea of what models are involved. This is a merge of pre-trained language models created using mergekit.
Merge Details
See Below
Merge Method
This model was merged using the passthrough merge method.
Models Merged
See Below
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: "Maid-Reborn-v22-10B"
layer_range: [0, 16]
- sources:
- model: "Maid-Reborn-v22-10B"
layer_range: [8, 24]
- sources:
- model: "Maid-Reborn-v22-10B"
layer_range: [17, 32]
merge_method: passthrough
dtype: float16
models:
- model: mistralai/Mistral-7B-v0.1
# No parameters necessary for base model
- model: cognitivecomputations/WestLake-7B-v2-laser
parameters:
density: 0.58
weight: [0.3877, 0.1636, 0.186, 0.0502]
- model: senseable/garten2-7b
parameters:
density: 0.58
weight: [0.234, 0.2423, 0.2148, 0.2775]
- model: berkeley-nest/Starling-LM-7B-alpha
parameters:
density: 0.58
weight: [0.1593, 0.1573, 0.1693, 0.3413]
- model: mlabonne/AlphaMonarch-7B
parameters:
density: 0.58
weight: [0.219, 0.4368, 0.4299, 0.331]
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: true
dtype: bfloat16
name: Maid-Reborn-v22
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