README.md

metadata

tags:
  - text-generation
  - autotrain_compatible
  - endpoints_compatible
  - chatml
  - text-generation-inference
  - transformers
  - slerp
  - mistral
  - mergekit
  - merge
base_model:
  - yam-peleg/Experiment26-7B
  - cognitivecomputations/dolphin-2.8-experiment26-7b
library_name: transformers
license: apache-2.0
language:
  - en
pipeline_tag: text-generation
thumbnail: >-
  https://huggingface.co/pabloce/Dolphin-2.8-slerp/resolve/main/Dolphin-28-slerp.jpeg

Dolphin-2.8-slerp - merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• yam-peleg/Experiment26-7B
• cognitivecomputations/dolphin-2.8-experiment26-7b

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: yam-peleg/Experiment26-7B
        layer_range: [0, 32]
      - model: cognitivecomputations/dolphin-2.8-experiment26-7b
        layer_range: [0, 32]
merge_method: slerp
base_model: yam-peleg/Experiment26-7B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16