README.md

metadata

base_model:
  - ehristoforu/0001lp
  - vicgalle/Configurable-Llama-3-8B-v0.2
  - cognitivecomputations/dolphin-2.9-llama3-8b
  - NeuralNovel/Llama-3-NeuralPaca-8b
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:

• ehristoforu/0001lp
• vicgalle/Configurable-Llama-3-8B-v0.2
• cognitivecomputations/dolphin-2.9-llama3-8b
• NeuralNovel/Llama-3-NeuralPaca-8b

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: ehristoforu/0001lp
      layer_range: [0, 32]
  - sources:
    - model: NeuralNovel/Llama-3-NeuralPaca-8b
      layer_range: [24, 32]
  - sources:
    - model: cognitivecomputations/dolphin-2.9-llama3-8b
      layer_range: [26, 32]
  - sources:
    - model: vicgalle/Configurable-Llama-3-8B-v0.2
      layer_range: [28, 32]
merge_method: passthrough
dtype: bfloat16