Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch
Paper
•
2311.03099
•
Published
•
30
This is a merge of pre-trained language models created using mergekit.
This model was merged using the DARE TIES merge method using /workspace/prototype-0.4x228 as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: /workspace/prototype-0.4x233
parameters:
weight: 0.2
density: 0.4
- model: /workspace/prototype-0.4x232
parameters:
weight: 0.2
density: 0.4
- model: /workspace/prototype-0.4x231
parameters:
weight: 0.2
density: 0.4
- model: /workspace/prototype-0.4x234
parameters:
weight: 0.2
density: 0.4
- model: /workspace/prototype-0.4x228
parameters:
weight: 0.2
density: 0.4
merge_method: dare_ties
base_model: /workspace/prototype-0.4x228
parameters:
normalize: false
chat_template: llama3
pad_to_multiple_of: 8
int8_mask: true
tokenizer:
source: base
dtype: bfloat16