base_model, library_name, tags, language
base_model library_name tags language
Qwen/Qwen2.5-3B
transformers
mergekit
merge
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, 6]
    model: Qwen/Qwen2.5-3B
- sources:
  - layer_range: [4, 12]
    model: Qwen/Qwen2.5-3B
- sources:
  - layer_range: [10, 18]
    model: Qwen/Qwen2.5-3B
- sources:
  - layer_range: [16, 24]
    model: Qwen/Qwen2.5-3B
- sources:
  - layer_range: [22, 30]
    model: Qwen/Qwen2.5-3B
- sources:
  - layer_range: [28, 36]
    model: Qwen/Qwen2.5-3B
merge_method: passthrough
dtype: bfloat16
Description
Model synced from source: qingy2024/Qwen2.5-4B
Readme 2 MiB