metadata
base_model:
- Qwen/Qwen2.5-7B-Instruct
library_name: transformers
tags:
- mergekit
- merge
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- layer_range: [0, 4]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [2, 6]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [4, 8]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [6, 10]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [8, 12]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [10, 14]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [12, 16]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [14, 18]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [16, 20]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [18, 22]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [20, 24]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [22, 26]
model: Qwen/Qwen2.5-7B-Instruct
- sources:
- layer_range: [24, 28]
model: Qwen/Qwen2.5-7B-Instruct
merge_method: passthrough
dtype: bfloat16
tokenizer_source: "Qwen/Qwen2.5-7B-Instruct"