Upload tokenizer
Browse files- chat_template.jinja +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +12 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if message['role'] == 'system' %}### INSTRUCTION:
|
| 2 |
+
{{ message['content'] }}
|
| 3 |
+
{% elif message['role'] == 'user' %}### INPUT:
|
| 4 |
+
{{ message['content'] }}
|
| 5 |
+
{% elif message['role'] == 'assistant' %}### OUTPUT:
|
| 6 |
+
{{ message['content'] }}
|
| 7 |
+
{% endif %}{% endfor %}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"model_max_length": 1024,
|
| 9 |
+
"pad_token": "<|endoftext|>",
|
| 10 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 11 |
+
"unk_token": "<|endoftext|>"
|
| 12 |
+
}
|