Anthony
commited on
Commit
•
e003e97
1
Parent(s):
5df38cf
Update tokenizer_config.json
Browse files- tokenizer_config.json +3 -1
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"50256": {
|
|
@@ -30,7 +31,8 @@
|
|
| 30 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 31 |
"clean_up_tokenization_spaces": true,
|
| 32 |
"eos_token": "<|im_end|>",
|
| 33 |
-
"
|
|
|
|
| 34 |
"pad_token": "<|endoftext|>",
|
| 35 |
"tokenizer_class": "GPT2Tokenizer",
|
| 36 |
"unk_token": "<|endoftext|>"
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
"add_prefix_space": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"50256": {
|
|
|
|
| 31 |
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 32 |
"clean_up_tokenization_spaces": true,
|
| 33 |
"eos_token": "<|im_end|>",
|
| 34 |
+
"errors": "replace",
|
| 35 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
"pad_token": "<|endoftext|>",
|
| 37 |
"tokenizer_class": "GPT2Tokenizer",
|
| 38 |
"unk_token": "<|endoftext|>"
|