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:
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