Model Stock: All we need is just a few fine-tuned models
Paper
•
2403.19522
•
Published
•
13
This is a merge of pre-trained language models created using mergekit.
This model was merged using the Model Stock merge method using ReadyArt/The-Omega-Abomination-L-70B-v1.0 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: ReadyArt/Fallen-Safeword-70B-R1-v4.1
- model: ReadyArt/Forgotten-Safeword-70B-v5.0
- model: ReadyArt/The-Omega-Directive-L-70B-v1.0
- model: ReadyArt/The-Omega-Abomination-L-70B-v1.0
base_model: ReadyArt/The-Omega-Abomination-L-70B-v1.0
merge_method: model_stock
dtype: float32
out_dtype: bfloat16
chat_template: llama3
tokenizer:
source: ReadyArt/The-Omega-Abomination-L-70B-v1.0