Iheb-Chaabane
commited on
Commit
•
a035bab
1
Parent(s):
79863c9
Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +0 -9
- tokenizer_config.json +2 -11
special_tokens_map.json
CHANGED
@@ -32,7 +32,7 @@
|
|
32 |
"single_word": false
|
33 |
},
|
34 |
"pad_token": {
|
35 |
-
"content": "
|
36 |
"lstrip": false,
|
37 |
"normalized": false,
|
38 |
"rstrip": false,
|
|
|
32 |
"single_word": false
|
33 |
},
|
34 |
"pad_token": {
|
35 |
+
"content": "<|endoftext|>",
|
36 |
"lstrip": false,
|
37 |
"normalized": false,
|
38 |
"rstrip": false,
|
tokenizer.json
CHANGED
@@ -18218,15 +18218,6 @@
|
|
18218 |
"rstrip": false,
|
18219 |
"normalized": false,
|
18220 |
"special": true
|
18221 |
-
},
|
18222 |
-
{
|
18223 |
-
"id": 131072,
|
18224 |
-
"content": "<pad>",
|
18225 |
-
"single_word": false,
|
18226 |
-
"lstrip": false,
|
18227 |
-
"rstrip": false,
|
18228 |
-
"normalized": false,
|
18229 |
-
"special": true
|
18230 |
}
|
18231 |
],
|
18232 |
"normalizer": null,
|
|
|
18218 |
"rstrip": false,
|
18219 |
"normalized": false,
|
18220 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18221 |
}
|
18222 |
],
|
18223 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -16192,14 +16192,6 @@
|
|
16192 |
"rstrip": false,
|
16193 |
"single_word": false,
|
16194 |
"special": true
|
16195 |
-
},
|
16196 |
-
"131072": {
|
16197 |
-
"content": "<pad>",
|
16198 |
-
"lstrip": false,
|
16199 |
-
"normalized": false,
|
16200 |
-
"rstrip": false,
|
16201 |
-
"single_word": false,
|
16202 |
-
"special": true
|
16203 |
}
|
16204 |
},
|
16205 |
"additional_special_tokens": [
|
@@ -16230,8 +16222,7 @@
|
|
16230 |
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n' + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}",
|
16231 |
"clean_up_tokenization_spaces": true,
|
16232 |
"eos_token": "<|endoftext|>",
|
16233 |
-
"model_max_length":
|
16234 |
-
"pad_token": "
|
16235 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
16236 |
}
|
16237 |
-
|
|
|
16192 |
"rstrip": false,
|
16193 |
"single_word": false,
|
16194 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16195 |
}
|
16196 |
},
|
16197 |
"additional_special_tokens": [
|
|
|
16222 |
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n' + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}",
|
16223 |
"clean_up_tokenization_spaces": true,
|
16224 |
"eos_token": "<|endoftext|>",
|
16225 |
+
"model_max_length": 8192,
|
16226 |
+
"pad_token": "<|endoftext|>",
|
16227 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
16228 |
}
|
|