weqweasdas
commited on
Commit
•
3042537
1
Parent(s):
6ac4b2e
Update README.md
Browse files
README.md
CHANGED
@@ -74,7 +74,7 @@ We train the model for one epoch with a learning rate of 1e-5, batch size 256, c
|
|
74 |
{"role": "user", "content": "I'd like to show off how chat templating works!"},
|
75 |
]
|
76 |
|
77 |
-
test_texts = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=False).replace(tokenizer.bos_token, "")
|
78 |
pipe_outputs = rm_pipe(test_texts, **pipe_kwargs)
|
79 |
rewards = [output[0]["score"] for output in pipe_outputs]
|
80 |
```
|
|
|
74 |
{"role": "user", "content": "I'd like to show off how chat templating works!"},
|
75 |
]
|
76 |
|
77 |
+
test_texts = [tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=False).replace(tokenizer.bos_token, "")]
|
78 |
pipe_outputs = rm_pipe(test_texts, **pipe_kwargs)
|
79 |
rewards = [output[0]["score"] for output in pipe_outputs]
|
80 |
```
|