This is just a test to see if I can improve my models by merging the Finnish data based model with the slightly higher performing English data based model.

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:

yaml

slices:
  - sources:
      - model: mpasila/Finnish-Viking-Alpaca-V1-7B
        layer_range: [0, 32]
      - model: mpasila/Alpacazord-Viking-7B
        layer_range: [0, 32]
# or, the equivalent models: syntax:
# models:
#   - model: psmathur/orca_mini_v3_13b
#   - model: garage-bAInd/Platypus2-13B
merge_method: slerp
base_model: mpasila/Finnish-Viking-Alpaca-V1-7B
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 # fallback for rest of tensors
dtype: float16

mpasila/Finnish-Alpacazord-7B

Finnish-Alpacazord-7B

Merge Details

Merge Method

Models Merged

Configuration

mpasila/
Finnish-Alpacazord-7B