isaacchung
commited on
Commit
•
26f90a7
1
Parent(s):
029a6e7
Upload tokenizer
Browse files- special_tokens_map.json +2 -13
- tokenizer.json +0 -18
- tokenizer_config.json +3 -24
special_tokens_map.json
CHANGED
@@ -1,24 +1,13 @@
|
|
1 |
{
|
2 |
-
"additional_special_tokens": [
|
3 |
-
"<|im_start|>",
|
4 |
-
"<|im_end|>"
|
5 |
-
],
|
6 |
"bos_token": {
|
7 |
-
"content": "<|
|
8 |
"lstrip": false,
|
9 |
"normalized": false,
|
10 |
"rstrip": false,
|
11 |
"single_word": false
|
12 |
},
|
13 |
"eos_token": {
|
14 |
-
"content": "<|
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": false,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false
|
19 |
-
},
|
20 |
-
"pad_token": {
|
21 |
-
"content": "<|im_end|>",
|
22 |
"lstrip": false,
|
23 |
"normalized": false,
|
24 |
"rstrip": false,
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
"lstrip": false,
|
5 |
"normalized": false,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
tokenizer.json
CHANGED
@@ -2306,24 +2306,6 @@
|
|
2306 |
"rstrip": false,
|
2307 |
"normalized": false,
|
2308 |
"special": true
|
2309 |
-
},
|
2310 |
-
{
|
2311 |
-
"id": 128256,
|
2312 |
-
"content": "<|im_start|>",
|
2313 |
-
"single_word": false,
|
2314 |
-
"lstrip": false,
|
2315 |
-
"rstrip": false,
|
2316 |
-
"normalized": false,
|
2317 |
-
"special": true
|
2318 |
-
},
|
2319 |
-
{
|
2320 |
-
"id": 128257,
|
2321 |
-
"content": "<|im_end|>",
|
2322 |
-
"single_word": false,
|
2323 |
-
"lstrip": false,
|
2324 |
-
"rstrip": false,
|
2325 |
-
"normalized": false,
|
2326 |
-
"special": true
|
2327 |
}
|
2328 |
],
|
2329 |
"normalizer": null,
|
|
|
2306 |
"rstrip": false,
|
2307 |
"normalized": false,
|
2308 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2309 |
}
|
2310 |
],
|
2311 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -2047,37 +2047,16 @@
|
|
2047 |
"rstrip": false,
|
2048 |
"single_word": false,
|
2049 |
"special": true
|
2050 |
-
},
|
2051 |
-
"128256": {
|
2052 |
-
"content": "<|im_start|>",
|
2053 |
-
"lstrip": false,
|
2054 |
-
"normalized": false,
|
2055 |
-
"rstrip": false,
|
2056 |
-
"single_word": false,
|
2057 |
-
"special": true
|
2058 |
-
},
|
2059 |
-
"128257": {
|
2060 |
-
"content": "<|im_end|>",
|
2061 |
-
"lstrip": false,
|
2062 |
-
"normalized": false,
|
2063 |
-
"rstrip": false,
|
2064 |
-
"single_word": false,
|
2065 |
-
"special": true
|
2066 |
}
|
2067 |
},
|
2068 |
-
"
|
2069 |
-
|
2070 |
-
"<|im_end|>"
|
2071 |
-
],
|
2072 |
-
"bos_token": "<|im_start|>",
|
2073 |
-
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
2074 |
"clean_up_tokenization_spaces": true,
|
2075 |
-
"eos_token": "<|
|
2076 |
"model_input_names": [
|
2077 |
"input_ids",
|
2078 |
"attention_mask"
|
2079 |
],
|
2080 |
"model_max_length": 1000000000000000019884624838656,
|
2081 |
-
"pad_token": "<|im_end|>",
|
2082 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2083 |
}
|
|
|
2047 |
"rstrip": false,
|
2048 |
"single_word": false,
|
2049 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
|
|
|
|
|
|
|
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|eot_id|>",
|
2056 |
"model_input_names": [
|
2057 |
"input_ids",
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
2061 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2062 |
}
|