Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +1 -1
- tokenizer_config.json +7 -5
special_tokens_map.json
CHANGED
@@ -7,7 +7,7 @@
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "<|
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "<|end_of_text|>",
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
tokenizer.json
CHANGED
@@ -14,7 +14,7 @@
|
|
14 |
},
|
15 |
{
|
16 |
"id": 128001,
|
17 |
-
"content": "<|
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
|
|
14 |
},
|
15 |
{
|
16 |
"id": 128001,
|
17 |
+
"content": "<|end_of_text|>",
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
@@ -9,7 +9,7 @@
|
|
9 |
"special": true
|
10 |
},
|
11 |
"128001": {
|
12 |
-
"content": "<|
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
@@ -2050,12 +2050,14 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
-
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
-
"eos_token": "<|
|
|
|
|
|
|
|
|
|
2056 |
"model_max_length": 131072,
|
2057 |
"pad_token": "<|finetune_right_pad_id|>",
|
2058 |
"padding_side": "left",
|
2059 |
-
"tokenizer_class": "PreTrainedTokenizerFast"
|
2060 |
-
"unk_token": null
|
2061 |
}
|
|
|
9 |
"special": true
|
10 |
},
|
11 |
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
+
"eos_token": "<|end_of_text|>",
|
2055 |
+
"model_input_names": [
|
2056 |
+
"input_ids",
|
2057 |
+
"attention_mask"
|
2058 |
+
],
|
2059 |
"model_max_length": 131072,
|
2060 |
"pad_token": "<|finetune_right_pad_id|>",
|
2061 |
"padding_side": "left",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
2063 |
}
|