Views
No views yet
$ pip install coref-onnx1from coref_onnx import CoreferenceResolver, decode_clusters
2
3resolver = CoreferenceResolver.from_pretrained("talmago/allennlp-coref-onnx-mMiniLMv2-L12-H384-distilled-from-XLMR-Large")
4
5sentences = [
6 ["Barack", "Obama", "was", "the", "44th", "President", "of", "the", "United", "States", "."],
7 ["He", "was", "born", "in", "Hawaii", "."]
8]
9
10pred = resolver(sentences)
11
12print("Clusters:", pred["clusters"][0])
13print("Decoded clusters:", decode_clusters(sentences, pred["clusters"][0]))Clusters: [[[(0, 1), (11, 11)]]]
Decoded clusters: [['Barack Obama', 'He']]1$ mkdir -p models/minillm
2$ wget -P models/minillm https://storage.googleapis.com/pandora-intelligence/models/crosslingual-coreference/minilm/model.tar.gz$ docker run -it --platform linux/amd64 --entrypoint /bin/bash -v $(pwd)/models/minillm:/models/minillm allennlp/allennlp:latestallennlp_models$ pip install allennlp_models1$ docker cp allennlp_models/coref/models/coref.py <CONTAINER_ID>:/opt/conda/lib/python3.8/site-packages/allennlp_models/coref/models/coref.py
2$ docker cp allennlp/nn/util.py <CONTAINER_ID>:/stage/allennlp/allennlp/nn/util.py
3$ docker cp export_onnx.py <CONTAINER_ID>:/app/export_onnx.py1$ mkdir nreimers
2$ git clone https://huggingface.co/nreimers/mMiniLMv2-L12-H384-distilled-from-XLMR-Large nreimers$ python export_onnx.pyonnxsim$ python -m onnxsim models/minillm/model.onnx optimized_model.onnx