Not at all. I should have made clear how I extracted in the post.
I extracted embeddings from a pytorch model (pytorch_model.bin file). The code to extract is pasted here. It assumes the embeddings are stored with the name bert.embeddings.word_embeddings.weight. You can just print out all the keys in your clinicalbert model and see what the key name exactly is.
md = torch.load(“./pytorch_model.bin”,map_location=’cpu’)
for k in md:
if (k == “bert.embeddings.word_embeddings.weight”):
embeds = md[k]
for l in range(len(embeds)):
vector = embeds[l]
for m in range(len(vector)):