Llama-3-Umbral-Mind-Instruct-8B

Copied the merge script from tannedbum/L3-Nymeria-8B and made it use OG Llama 3 Instruct with Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B as the base model instead.

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:

• Undi95/Meta-Llama-3-8B-Instruct-hf
• Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
        layer_range: [0, 32]
      - model: Undi95/Meta-Llama-3-8B-Instruct-hf
        layer_range: [0, 32]
merge_method: slerp
base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
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