juni4 / README.md
JuniperChinenye's picture
Upload LlamaForCausalLM
9449a0e verified
metadata
base_model:
  - Grayx/fiufiu_71
  - luaqi/sn37_v3
library_name: transformers
tags:
  - mergekit
  - merge

merge

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: Grayx/fiufiu_71
        layer_range: [0, 28]
      - model: luaqi/sn37_v3
        layer_range: [0, 28]
merge_method: slerp
base_model: luaqi/sn37_v3
parameters:
  t:
    - filter: self_attn
      value: [0, 0.7, 0.5, 0.8, 1]
    - filter: mlp
      value: [1, 0.3, 0.5, 0.2, 0]
    - value: 0.6 # fallback for rest of tensors
dtype: float16