Run hugging-face BART model decoder with a BART encoder which has had the attention heads overwritten

Question

I am looking to build a pipeline that applies the hugging-face BART model step-by-step. Once I have built the pipeline, I will be looking to substitute the encoder attention heads with a pre-trained / pre-defined encoder attention head.

The pipeline I will be looking to implement is as follows:

1. Tokenize input
2. Run the tokenized input through the encoder with an adjusted attention layer
3. Run the output through the decoder
4. change output of decoder into text summary

At the moment my code looks like the below with comments where I am stuck

from transformers import AutoTokenizer, AutoModel, BartConfig, EncoderDecoderModel

article = """Text to be summarised."""

model_name = "facebook/bart-large-cnn"

# Values of dictionaries are tensors
attention_heads = {"Cars": cars_encoder_attention_layer, 
                   "Countries": countries_encoder_attention_layer
                  }

model_name = "facebook/bart-large-cnn"
config = BartConfig.from_pretrained(model_name, output_hidden_states=True, output_attention=True)
tokenizer = AutoTokenizer.from_pretrained(model_name)
inputs = tokenizer(article, padding=True, truncation=True, return_tensors="pt")
model = AutoModel.from_pretrained(model_name)
model.config.output_attentions = True
outputs = model(**inputs)

# Overwrite the encoder attentions with the desired attention heads
outputs.encoder_attentions = attention_heads ["Cars"]

# Here I would take the overwritten encoder and insert into the decoder to generate the summary with the adjusted attention heads