Upload tokenizer
Browse files- .gitattributes +1 -0
- chat_template.jinja +15 -0
- special_tokens_map.json +16 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{'<extra_id_0>System'}}{% for message in messages %}{% if message['role'] == 'system' %}{{'
|
| 2 |
+
' + message['content'].strip()}}{% if tools or contexts %}{{'
|
| 3 |
+
'}}{% endif %}{% endif %}{% endfor %}{% if tools %}{% for tool in tools %}{{ '
|
| 4 |
+
<tool> ' + tool|tojson + ' </tool>' }}{% endfor %}{% endif %}{% if contexts %}{% if tools %}{{'
|
| 5 |
+
'}}{% endif %}{% for context in contexts %}{{ '
|
| 6 |
+
<context> ' + context.strip() + ' </context>' }}{% endfor %}{% endif %}{{'
|
| 7 |
+
|
| 8 |
+
'}}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<extra_id_1>User
|
| 9 |
+
' + message['content'].strip() + '
|
| 10 |
+
' }}{% elif message['role'] == 'assistant' %}{{ '<extra_id_1>Assistant
|
| 11 |
+
' + message['content'].strip() + '
|
| 12 |
+
' }}{% elif message['role'] == 'tool' %}{{ '<extra_id_1>Tool
|
| 13 |
+
' + message['content'].strip() + '
|
| 14 |
+
' }}{% endif %}{% endfor %}{%- if add_generation_prompt %}{{'<extra_id_1>Assistant
|
| 15 |
+
'}}{%- endif %}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
}
|
| 16 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91fd32f29cfeb8fee9535681f551697b066992c9d950d810651801be24f39e93
|
| 3 |
+
size 34809710
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|