This is a merge of pre-trained language models created using
mergekit.
In theory, context length has been extended to 32K tokens. In practice? Degradation above 8K context length.
Tested with ChatML instruct prompts, temperature 1.0, and minP 0.01, but feel free to experiment.
This model was merged using the
task arithmetic merge method using
grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B as a base.
1base_model: grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B
2dtype: bfloat16
3merge_method: task_arithmetic
4slices:
5- sources:
6 - layer_range: [0, 32]
7 model: grimjim/Mistral-7B-Instruct-demi-merge-v0.2-7B
8 - layer_range: [0, 32]
9 model: lucyknada/microsoft_WizardLM-2-7B
10 parameters:
11 weight: 1.00
12
