Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 18
This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using mattshumer/Reflection-Llama-3.1-70B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: mattshumer/Reflection-Llama-3.1-70B
parameters:
weight: 0.8
- model: Sao10K/L3-70B-Euryale-v2.1
parameters:
weight: 0.2
merge_method: ties
base_model: mattshumer/Reflection-Llama-3.1-70B
parameters:
density: 0.7
normalize: true
dtype: float16
tokenizer_source: base