djuna's picture
Upload folder using huggingface_hub
634292f verified
|
raw
history blame
3.04 kB
metadata
base_model:
  - Qwen/Qwen2.5-Coder-1.5B-Instruct
  - Etherll/Qwen2.5-Coder-1.5B-CodeFIM
library_name: transformers
tags:
  - mergekit
  - merge

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, 1]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [1, 2]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
- sources:
  - layer_range: [3, 3]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [3, 4]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
- sources:
  - layer_range: [5, 5]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [5, 6]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
- sources:
  - layer_range: [7, 7]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [7, 8]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
- sources:
  - layer_range: [9, 9]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [9, 10]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
- sources:
  - layer_range: [11, 11]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [11, 12]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
- sources:
  - layer_range: [13, 13]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [13, 14]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
- sources:
  - layer_range: [15, 15]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [15, 16]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
- sources:
  - layer_range: [17, 17]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [17, 18]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
- sources:
  - layer_range: [19, 19]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [19, 20]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
- sources:
  - layer_range: [21, 21]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [21, 22]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
- sources:
  - layer_range: [23, 23]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [23, 24]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
- sources:
  - layer_range: [25, 25]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [25, 26]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
- sources:
  - layer_range: [27, 27]
    model: Qwen/Qwen2.5-Coder-1.5B-Instruct
- sources:
  - layer_range: [27, 28]
    model: Etherll/Qwen2.5-Coder-1.5B-CodeFIM
merge_method: passthrough
dtype: bfloat16