L3.1-RPGramMax-1.5 / README.md
djuna's picture
Upload folder using huggingface_hub
d940d0c verified
|
raw
history blame
No virus
1 kB
metadata
base_model:
  - ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
  - djuna/L3.1-gramamax
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:

models:
  - model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
  - model: djuna/L3.1-gramamax
merge_method: slerp
base_model: djuna/L3.1-gramamax
parameters:
  int8_mask: true
  t:
    - filter: self_attn
      value: [0.5, 0.5, 0.4, 0.7, 1]
    - filter: mlp
      value: [0.5, 0.5, 0.6, 0.3, 0]
    - value: 0.5
dtype: bfloat16