metadata
base_model:
- Casual-Autopsy/Llama-3-Yollow-SCE
- lmg-anon/vntl-llama3-8b-v2-qlora
library_name: transformers
tags:
- mergekit
- merge
language:
- en
- ja
pipeline_tag: translation
Disclaimer: Set logit bias for <|eot_id|> to 5 and Top K to 1
Model uses vntl llama3 8b v2 instruct formatting and prompting
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the TIES merge method using Casual-Autopsy/Llama-3-Yollow-SCE as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Casual-Autopsy/Llama-3-Yollow-SCE+lmg-anon/vntl-llama3-8b-v2-qlora
parameters:
density: 0.85
weight: 0.5
merge_method: ties
base_model: Casual-Autopsy/Llama-3-Yollow-SCE
parameters:
normalize: false
dtype: bfloat16