Upload tokenizer
Browse files- README.md +1 -1
- tokenizer_config.json +1 -0
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
language:
|
| 4 |
- de
|
|
|
|
| 5 |
tags:
|
| 6 |
- dpo
|
| 7 |
- alignment-handbook
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
language:
|
| 3 |
- de
|
| 4 |
+
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
- dpo
|
| 7 |
- alignment-handbook
|
tokenizer_config.json
CHANGED
|
@@ -33,6 +33,7 @@
|
|
| 33 |
"</s>"
|
| 34 |
],
|
| 35 |
"bos_token": "<s>",
|
|
|
|
| 36 |
"clean_up_tokenization_spaces": false,
|
| 37 |
"eos_token": "</s>",
|
| 38 |
"legacy": true,
|
|
|
|
| 33 |
"</s>"
|
| 34 |
],
|
| 35 |
"bos_token": "<s>",
|
| 36 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 37 |
"clean_up_tokenization_spaces": false,
|
| 38 |
"eos_token": "</s>",
|
| 39 |
"legacy": true,
|