Update README.md

README.md

@@ -43,7 +43,7 @@ import torch
 
 tokenizer = T5Tokenizer.from_pretrained('Rostlab/prot_t5_xl_half_uniref50-enc', do_lower_case=False)
 
-model = T5EncoderModel.from_pretrained("Rostlab/prot_t5_xl_half_uniref50-enc")
+model = T5EncoderModel.from_pretrained("Rostlab/prot_t5_xl_half_uniref50-enc", torch_dtype=torch.float16)
 
 sequences_Example = ["A E T C Z A O","S K T Z P"]
 
@@ -60,6 +60,7 @@ emb_0 = embedding_repr.last_hidden_state[0,:6]
 emb_1 = embedding_repr.last_hidden_state[1,:4] 
 ```
 
+**NOTE**: Please make sure to explicitly set the model to `float16` (`T5EncoderModel.from_pretrained('Rostlab/prot_t5_xl_half_uniref50-enc', torch_dtype=torch.float16)`) otherwise, the generated embeddings will be full precision. 
 
 ### BibTeX entry and citation info