README.md

metadata

base_model:
  - tannedbum/L3-Nymeria-v2-8B
  - elyza/Llama-3-ELYZA-JP-8B
library_name: transformers
tags:
  - mergekit
  - merge
license: llama3
language:
  - en
  - ja

Llama-3-Nymeria-ELYZA-8B

Experimental merge between a Llama 3 model that has had continued pre-training with Japanese data and a regular RP model to see how well it keeps its Japanese capability and RP capability.

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:

• tannedbum/L3-Nymeria-v2-8B
• elyza/Llama-3-ELYZA-JP-8B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: tannedbum/L3-Nymeria-v2-8B
        layer_range: [0, 32]
      - model: elyza/Llama-3-ELYZA-JP-8B
        layer_range: [0, 32]
merge_method: slerp
base_model: tannedbum/L3-Nymeria-v2-8B
parameters:
  t:
    - filter: self_attn
      value: [0.4, 0.5, 0.6, 0.4, 0.6]
    - filter: mlp
      value: [0.6, 0.5, 0.4, 0.6, 0.4]
    - value: 0.5
dtype: bfloat16