This is a merge of pre-trained language models created using
mergekit.
This model was merged using the passthrough merge method.
1
2dtype: float16
3merge_method: passthrough
4slices:
5- sources:
6 - layer_range: [0, 5]
7 model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
8- sources:
9 - layer_range: [3, 10]
10 model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
11- sources:
12 - layer_range: [10, 15]
13 model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
14- sources:
15 - layer_range: [15, 20]
16 model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
17
18
