Update README.md
Browse files
README.md
CHANGED
@@ -64,7 +64,7 @@ message = [
|
|
64 |
message_template = tokenizer.apply_chat_template(message, tokenize=False)
|
65 |
# it will look like this: "<s><s> [INST] I'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? [/INST]Sorry, 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?</s>"
|
66 |
|
67 |
-
kwargs = {"padding": '
|
68 |
tokens = tokenizer.encode_plus(message_template, **kwargs)
|
69 |
|
70 |
with torch.no_grad():
|
|
|
64 |
message_template = tokenizer.apply_chat_template(message, tokenize=False)
|
65 |
# it will look like this: "<s><s> [INST] I'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? [/INST]Sorry, 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?</s>"
|
66 |
|
67 |
+
kwargs = {"padding": 'longest', "truncation": True, "return_tensors": "pt"}
|
68 |
tokens = tokenizer.encode_plus(message_template, **kwargs)
|
69 |
|
70 |
with torch.no_grad():
|