#how-to: https://github.com/allenai/allennlp/blob/master/tutorials/how_to/elmo.md #example python code to read the embeddings > import h5py > h5py_file = h5py.File("ALL.data.average.hdf5", 'r') > embedding = h5py_file.get("0") # embedding of the first sentence (average of three elmo layers) > len(embedding) 25 # length of the first sentence > len(embedding[0]) 1024 # embedding of the first token of the sentence (each embedding has dim 1024)