Update default tokenization behavior to "longest" in README (#2)

- Update default tokenization behavior to "longest" in README (7944c25c016612486d38062898876df63305635f)

Co-authored-by: Michael Ryan <[email protected]>

Files changed (1) hide show

README.md CHANGED Viewed

@@ -65,7 +65,7 @@ message = [
 message_template = tokenizer.apply_chat_template(message, tokenize=False)
 # it will look like this: "<bos><start_of_turn>user\nI'm going to go out to a movie, but I need someone to chat with my daughter and pretend to be me while she's home alone.  But I can't do that while I'm at the movie.  Can you help by impersonating me by chat with her?<end_of_turn>\n<start_of_turn>model\nSorry, I'm not comfortable impersonating you in that way.  I'm not willing to behave so dishonestly.  Maybe you can just find a way to bring her to the movie, or you can find a babysitter?<end_of_turn>\n".
-kwargs = {"padding": 'max_length', "truncation": True, "return_tensors": "pt"}
 tokens = tokenizer.encode_plus(message_template, **kwargs)
 with torch.no_grad():

 message_template = tokenizer.apply_chat_template(message, tokenize=False)
 # it will look like this: "<bos><start_of_turn>user\nI'm going to go out to a movie, but I need someone to chat with my daughter and pretend to be me while she's home alone.  But I can't do that while I'm at the movie.  Can you help by impersonating me by chat with her?<end_of_turn>\n<start_of_turn>model\nSorry, I'm not comfortable impersonating you in that way.  I'm not willing to behave so dishonestly.  Maybe you can just find a way to bring her to the movie, or you can find a babysitter?<end_of_turn>\n".
+kwargs = {"padding": 'longest', "truncation": True, "return_tensors": "pt"}
 tokens = tokenizer.encode_plus(message_template, **kwargs)
 with torch.no_grad():