Through my wanderings around huggingface I came across a model merging method I had not seen before and decided to test it out using the ingredients from my Progenitor merges. I am not sure if it's because of SicariusSicariiStuff/Negative_LLAMA_70B as the pivot model, but it seems a lot 'hornier'. Its style is nice, but I am not sure if it outright beats Progenitor 1.1 (techinically it is the same incredients only mixed differently.)
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SCE merge method using nbeerbower/Llama-3.1-Nemotron-lorablated-70B as a base.
Models Merged
The following models were included in the merge:
- TheDrummer/Anubis-70B-v1
- Sao10K/L3.1-70B-Hanami-x1
- EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
- SicariusSicariiStuff/Negative_LLAMA_70B
- Sao10K/70B-L3.3-Cirrus-x1
Configuration
The following YAML configuration was used to produce this model:
models:
# Pivot model
- model: SicariusSicariiStuff/Negative_LLAMA_70B
# Target models
- model: Sao10K/70B-L3.3-Cirrus-x1
- model: Sao10K/L3.1-70B-Hanami-x1
- model: TheDrummer/Anubis-70B-v1
- model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
merge_method: sce
base_model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
parameters:
select_topk: 1.0
dtype: bfloat16