Upload tokenizer
Browse files- chat_template.jinja +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '
|
| 2 |
+
|
| 3 |
+
' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '
|
| 4 |
+
|
| 5 |
+
' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"model_max_length": 4096,
|
| 9 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 10 |
+
"sp_model_kwargs": {},
|
| 11 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 12 |
+
"unk_token": null,
|
| 13 |
+
"use_default_system_prompt": false
|
| 14 |
+
}
|