Upload 3 files
Browse files- special_tokens_map.json +21 -2
- tokenizer.json +3 -2
- tokenizer_config.json +4 -3
special_tokens_map.json
CHANGED
@@ -1,4 +1,23 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
}
|
|
|
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": "<|end_of_text|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
}
|
tokenizer.json
CHANGED
@@ -2300,7 +2300,7 @@
|
|
2300 |
},
|
2301 |
{
|
2302 |
"id": 128255,
|
2303 |
-
"content": "
|
2304 |
"single_word": false,
|
2305 |
"lstrip": false,
|
2306 |
"rstrip": false,
|
@@ -2348,6 +2348,7 @@
|
|
2348 |
"end_of_word_suffix": null,
|
2349 |
"fuse_unk": false,
|
2350 |
"byte_fallback": false,
|
|
|
2351 |
"vocab": {
|
2352 |
"!": 0,
|
2353 |
"\"": 1,
|
@@ -410500,4 +410501,4 @@
|
|
410500 |
"éĶ ¦"
|
410501 |
]
|
410502 |
}
|
410503 |
-
}
|
|
|
2300 |
},
|
2301 |
{
|
2302 |
"id": 128255,
|
2303 |
+
"content": "<pad>",
|
2304 |
"single_word": false,
|
2305 |
"lstrip": false,
|
2306 |
"rstrip": false,
|
|
|
2348 |
"end_of_word_suffix": null,
|
2349 |
"fuse_unk": false,
|
2350 |
"byte_fallback": false,
|
2351 |
+
"ignore_merges": false,
|
2352 |
"vocab": {
|
2353 |
"!": 0,
|
2354 |
"\"": 1,
|
|
|
410501 |
"éĶ ¦"
|
410502 |
]
|
410503 |
}
|
410504 |
+
}
|
tokenizer_config.json
CHANGED
@@ -2041,7 +2041,7 @@
|
|
2041 |
"special": true
|
2042 |
},
|
2043 |
"128255": {
|
2044 |
-
"content": "
|
2045 |
"lstrip": false,
|
2046 |
"normalized": false,
|
2047 |
"rstrip": false,
|
@@ -2050,6 +2050,7 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
"eos_token": "<|end_of_text|>",
|
2055 |
"model_input_names": [
|
@@ -2057,6 +2058,6 @@
|
|
2057 |
"attention_mask"
|
2058 |
],
|
2059 |
"model_max_length": 1000000000000000019884624838656,
|
2060 |
-
"
|
2061 |
-
"
|
2062 |
}
|
|
|
2041 |
"special": true
|
2042 |
},
|
2043 |
"128255": {
|
2044 |
+
"content": "<pad>",
|
2045 |
"lstrip": false,
|
2046 |
"normalized": false,
|
2047 |
"rstrip": false,
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|end_of_text|>",
|
2056 |
"model_input_names": [
|
|
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 1000000000000000019884624838656,
|
2061 |
+
"pad_token": "<pad>",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
}
|