This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
task arithmetic merge method using
arcee-ai/llama_from_mistral_instruct_v2 as a base.
1models:
2 - model: arcee-ai/llama_from_mistral_instruct_v2
3 parameters:
4 weight: 0.5
5 - model: NousResearch/Llama-2-7b-chat-hf
6 parameters:
7 weight: 0.5
8
9merge_method: task_arithmetic
10base_model: arcee-ai/llama_from_mistral_instruct_v2
11parameters:
12 normalize: true
13 int8_mask: true
14
15dtype: bfloat16
