MergeKitBot's picture
Upload folder using huggingface_hub
82c40fd verified
|
raw
history blame
2.03 kB
metadata
base_model:
  - cognitivecomputations/dolphin-2.9.1-yi-1.5-34b
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 using cognitivecomputations/dolphin-2.9.1-yi-1.5-34b as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: "cognitivecomputations/dolphin-2.9.1-yi-1.5-34b"
        layer_range: [0, 10]
  - sources:
      - model: "cognitivecomputations/dolphin-2.9.1-yi-1.5-34b"
        layer_range: [12, 14]
  - sources:
      - model: "cognitivecomputations/dolphin-2.9.1-yi-1.5-34b"
        layer_range: [16, 18]
  - sources:
      - model: "cognitivecomputations/dolphin-2.9.1-yi-1.5-34b"
        layer_range: [20,22]
  - sources:
      - model: "cognitivecomputations/dolphin-2.9.1-yi-1.5-34b"
        layer_range: [24, 26]
  - sources:
      - model: "cognitivecomputations/dolphin-2.9.1-yi-1.5-34b"
        layer_range: [28,30]
  - sources:
      - model: "cognitivecomputations/dolphin-2.9.1-yi-1.5-34b"
        layer_range: [32, 34]
  - sources:
      - model: "cognitivecomputations/dolphin-2.9.1-yi-1.5-34b"
        layer_range: [36,38]
  - sources:
      - model: "cognitivecomputations/dolphin-2.9.1-yi-1.5-34b"
        layer_range: [40, 42]
  - sources:
      - model: "cognitivecomputations/dolphin-2.9.1-yi-1.5-34b"
        layer_range: [44,46]
  - sources:
      - model: "cognitivecomputations/dolphin-2.9.1-yi-1.5-34b"
        layer_range: [48, 50]
  - sources:
      - model: "cognitivecomputations/dolphin-2.9.1-yi-1.5-34b"
        layer_range: [50,60]
merge_method: passthrough
base_model: "cognitivecomputations/dolphin-2.9.1-yi-1.5-34b"
dtype: bfloat16