Adapter doncamilom/OChemSegm-flan-T5-large for google/flan-t5-large

An adapter for the google/flan-t5-large model that was trained on the USPTO-segment dataset.

This adapter was created for usage with the adapter-transformers library.

Usage

First, install adapter-transformers:

pip install -U adapter-transformers

Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. More

Now, the adapter can be loaded and activated like this:

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

adapter = 'doncamilom/OChemSegm-flan-T5-large'

model = AutoModelForSeq2SeqLM.from_pretrained(
    'google/flan-t5-large',
)

# Load adapter
adapter_name = self.model.load_adapter(adapter, source='hf', set_active=True)

# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained(adapter)

Architecture & Training

Evaluation results

Citation