This model is part of a series of experiments in merging some of my favorite Llama models, an idea which was based on the excellent Steelskull/L3.3-MS-Nevoria-70b merge, just with a couple of extra ingredients and different merge methods. Here I tried a Della Linear merge with default parameters. Against my better judgement I thought the newer Sao10K/L3.3-70B-Euryale-v2.3 would be better in the mix than Sao10K/L3.1-70B-Hanami-x1 (which has a very special place in my heart). The results were decent. Though Tarek07/Progenitor-V1.1-LLaMa-70B still comes out on top (imo).
This is a merge of pre-trained language models created using
mergekit.
This model was merged using the della_linear merge method using
nbeerbower/Llama-3.1-Nemotron-lorablated-70B as a base.
1models:
2 - model: Sao10K/L3.3-70B-Euryale-v2.3
3 parameters:
4 weight: 0.20
5 - model: Sao10K/70B-L3.3-Cirrus-x1
6 parameters:
7 weight: 0.20
8 - model: SicariusSicariiStuff/Negative_LLAMA_70B
9 parameters:
10 weight: 0.20
11 - model: TheDrummer/Anubis-70B-v1
12 parameters:
13 weight: 0.20
14 - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
15 parameters:
16 weight: 0.20
17merge_method: della_linear
18base_model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
19dtype: bfloat16
