README.md

metadata

base_model: []
library_name: transformers
tags:
  - mergekit
  - merge

Llama-3.1-SuperNova-Lite-14B

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:

• /Users/jsarnecki/opt/Workspace/arcee-ai/Llama-3.1-SuperNova-Lite

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
    - model: "/Users/jsarnecki/opt/Workspace/arcee-ai/Llama-3.1-SuperNova-Lite" 
      layer_range: [0, 8]

  - sources:
    - model: "/Users/jsarnecki/opt/Workspace/arcee-ai/Llama-3.1-SuperNova-Lite" 
      layer_range: [4, 12]

  - sources:
    - model: "/Users/jsarnecki/opt/Workspace/arcee-ai/Llama-3.1-SuperNova-Lite" 
      layer_range: [8, 16]

  - sources:
    - model: "/Users/jsarnecki/opt/Workspace/arcee-ai/Llama-3.1-SuperNova-Lite" 
      layer_range: [12, 20]

  - sources:
    - model: "/Users/jsarnecki/opt/Workspace/arcee-ai/Llama-3.1-SuperNova-Lite" 
      layer_range: [16, 24]
  
  - sources:
    - model: "/Users/jsarnecki/opt/Workspace/arcee-ai/Llama-3.1-SuperNova-Lite" 
      layer_range: [20, 28]

  - sources:
    - model: "/Users/jsarnecki/opt/Workspace/arcee-ai/Llama-3.1-SuperNova-Lite" 
      layer_range: [24, 32]

merge_method: passthrough
dtype: float32
out_dtype: bfloat16