Triangle104's picture
Update README.md
5a804ba verified
|
raw
history blame
1.12 kB
metadata
base_model:
  - unsloth/Llama-3.3-70B-Instruct
  - nbeerbower/Llama3.1-Gutenberg-Doppel-70B
library_name: transformers
tags:
  - mergekit
  - merge
license: llama3.3

Merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Credit goes to Unsloth for Base model and nbeerbower for Gutenberg-Doppel model.

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: unsloth/Llama-3.3-70B-Instruct
  - model: nbeerbower/Llama3.1-Gutenberg-Doppel-70B
merge_method: slerp
base_model: unsloth/Llama-3.3-70B-Instruct
dtype: bfloat16
parameters:
  t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Llama for input & output, Gutenberg-Doppel in the middle layers