metadata
base_model:
- TareksLab/Anathema-V8-LLaMA-70B
- TareksLab/Cortex-V4-LLaMA-70B
- TareksLab/Wordsmith-V7-LLaMa-70B
- TareksLab/Scrivener-Base-V6-LLaMA-70B
- TareksLab/RolePlayer-V6-LLaMa-70B
library_name: transformers
tags:
- mergekit
- merge
MERGE2
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the DELLA merge method using TareksLab/Scrivener-Base-V6-LLaMA-70B as a base.
Models Merged
The following models were included in the merge:
- TareksLab/Anathema-V8-LLaMA-70B
- TareksLab/Cortex-V4-LLaMA-70B
- TareksLab/Wordsmith-V7-LLaMa-70B
- TareksLab/RolePlayer-V6-LLaMa-70B
Configuration
The following YAML configuration was used to produce this model:
models:
- model: TareksLab/Wordsmith-V7-LLaMa-70B
parameters:
weight: 0.20
density: 0.5
epsilon: 0.1
lambda: 1.0
- model: TareksLab/Anathema-V8-LLaMA-70B
parameters:
weight: 0.20
density: 0.5
epsilon: 0.1
lambda: 1.0
- model: TareksLab/Scrivener-Base-V6-LLaMA-70B
parameters:
weight: 0.20
density: 0.5
epsilon: 0.1
lambda: 1.0
- model: TareksLab/RolePlayer-V6-LLaMa-70B
parameters:
weight: 0.20
density: 0.5
epsilon: 0.1
lambda: 1.0
- model: TareksLab/Cortex-V4-LLaMA-70B
parameters:
weight: 0.20
density: 0.5
epsilon: 0.1
lambda: 1.0
merge_method: della
base_model: TareksLab/Scrivener-Base-V6-LLaMA-70B
parameters:
normalize: false
dtype: bfloat16
chat_template: llama3
tokenizer:
source: TareksLab/Cortex-V4-LLaMA-70B