This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
TIES merge method using
NousResearch/Llama-2-7b-hf as a base.
1models:
2 - model: abhinand/malayalam-llama-7b-instruct-v0.1
3 parameters:
4 density: 0.5
5 weight: 0.5
6 - model: Finnish-NLP/llama-7b-finnish-instruct-v0.2
7 parameters:
8 density: 0.5
9 weight: 0.5
10
11merge_method: ties
12base_model: NousResearch/Llama-2-7b-hf
13parameters:
14 normalize: false
15 int8_mask: true
16dtype: float16
17
