This is a merge of two leading Hermes models created using
LazyMergekit, combining OpenHermes's robust capabilities with Nous-Hermes-DPO's refined instruction following.
I'm David Soeiro-Vuong, a third-year Computer Science student working as an apprentice at TW3 Partners, a company specialized in Generative AI. Passionate about artificial intelligence and language models optimization, I focus on creating efficient model merges that balance performance and capabilities.
This model uses SLERP (Spherical Linear Interpolation) with carefully tuned parameters:
1slices:
2 - sources:
3 - model: teknium/OpenHermes-2.5-Mistral-7B
4 layer_range: [0, 32]
5 - model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
6 layer_range: [0, 32]
7merge_method: slerp
8base_model: teknium/OpenHermes-2.5-Mistral-7B
9parameters:
10 t:
11 - filter: self_attn
12 value: [0, 0.5, 0.3, 0.7, 1]
13 - filter: mlp
14 value: [1, 0.5, 0.7, 0.3, 0]
15 - value: 0.5
16dtype: bfloat16
