temp: 1
min P: 0.02
top nsigma: 2.23
rep pen: 1.02 - 1.04
DRY: {0.7, 1.4, 3, 4096} - {0.8, 1.4, 5, 4096}
This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
Model Stock merge method using
huihui-ai/Llama-3.3-70B-Instruct-abliterated as a base.
1models:
2 - model: "D:\\mergekit\\LORAs\\applied\\Book_RPv05"
3 - model: "D:\\mergekit\\LORAs\\applied\\Book_RPv1"
4 - model: "D:\\mergekit\\LORAs\\applied\\Book_RPv15"
5 - model: "D:\\mergekit\\LORAs\\applied\\Book_RPvfinal"
6 - model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
7base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated
8merge_method: model_stock
9dtype: float32
10out_dtype: bfloat16
11chat_template: llama3
12tokenizer:
13 source: union
