Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 19
How to use mllm-dev/merge_yelp_droid_ties_2 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-classification", model="mllm-dev/merge_yelp_droid_ties_2") # Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("mllm-dev/merge_yelp_droid_ties_2")
model = AutoModelForSequenceClassification.from_pretrained("mllm-dev/merge_yelp_droid_ties_2")This is a merge of pre-trained language models created using mergekit.
This model was merged using the TIES merge method using mllm-dev/merge_diff_data_DROID as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
base_model: mllm-dev/merge_diff_data_DROID
dtype: float16
merge_method: ties
slices:
- sources:
- layer_range: [0, 12]
model: mllm-dev/merge_diff_data_DROID
parameters:
weight: 0.5
- layer_range: [0, 12]
model: mllm-dev/merge_diff_data_YELP
parameters:
weight: 0.5