Upload tokenizer
Browse files- tokenizer.json +6 -1
- tokenizer_config.json +4 -0
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 1024,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
tokenizer_config.json
CHANGED
@@ -318,8 +318,12 @@
|
|
318 |
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
319 |
"clean_up_tokenization_spaces": true,
|
320 |
"eos_token": "<|endoftext|>",
|
|
|
321 |
"model_max_length": 2048,
|
322 |
"pad_token": "<|endoftext|>",
|
|
|
323 |
"tokenizer_class": "CodeGenTokenizer",
|
|
|
|
|
324 |
"unk_token": "<|endoftext|>"
|
325 |
}
|
|
|
318 |
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
319 |
"clean_up_tokenization_spaces": true,
|
320 |
"eos_token": "<|endoftext|>",
|
321 |
+
"max_length": 1024,
|
322 |
"model_max_length": 2048,
|
323 |
"pad_token": "<|endoftext|>",
|
324 |
+
"stride": 0,
|
325 |
"tokenizer_class": "CodeGenTokenizer",
|
326 |
+
"truncation_side": "right",
|
327 |
+
"truncation_strategy": "longest_first",
|
328 |
"unk_token": "<|endoftext|>"
|
329 |
}
|