README.md

metadata

base_model:
  - meta-llama/Meta-Llama-3-8B
library_name: transformers
tags:
  - mergekit
  - merge
  - llama3
license: llama3
language:
  - en

Meta's Llama 3 8B pruned to 7B parameters(w/ 28 layers). Layers to prune selected using PruneMe repo on Github.

• layers_to_skip = 4

• Layer 23 to 27 has the minimum average distance of 0.18376044921875

• To Do : Post pruning training.

model

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:

• meta-llama/Meta-Llama-3-8B

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: meta-llama/Meta-Llama-3-8B
        layer_range: [0, 23]
  - sources:
      - model: meta-llama/Meta-Llama-3-8B
        layer_range: [27,32]
            
merge_method: passthrough
dtype: bfloat16