Upload tokenizer_config.json
Browse files- tokenizer_config.json +8 -45
tokenizer_config.json
CHANGED
@@ -1,50 +1,13 @@
|
|
1 |
{
|
2 |
-
"add_bos_token":
|
3 |
"add_eos_token": false,
|
4 |
-
"added_tokens_decoder": {
|
5 |
-
"0": {
|
6 |
-
"content": "<unk>",
|
7 |
-
"lstrip": false,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false,
|
11 |
-
"special": true
|
12 |
-
},
|
13 |
-
"1": {
|
14 |
-
"content": "<s>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": false,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false,
|
19 |
-
"special": true
|
20 |
-
},
|
21 |
-
"2": {
|
22 |
-
"content": "</s>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": false,
|
25 |
-
"rstrip": false,
|
26 |
-
"single_word": false,
|
27 |
-
"special": true
|
28 |
-
}
|
29 |
-
},
|
30 |
-
"additional_special_tokens": [],
|
31 |
-
"bos_token": "<s>",
|
32 |
-
"chat_template": null,
|
33 |
-
"clean_up_tokenization_spaces": false,
|
34 |
-
"cls_token": null,
|
35 |
-
"eos_token": "</s>",
|
36 |
-
"mask_token": null,
|
37 |
-
"model_input_names": [
|
38 |
-
"input_ids",
|
39 |
-
"attention_mask"
|
40 |
-
],
|
41 |
"model_max_length": 4096,
|
42 |
-
"pad_token": "</s>",
|
43 |
-
"padding_side": "left",
|
44 |
-
"sep_token": null,
|
45 |
-
"split_special_tokens": false,
|
46 |
-
"tokenizer_class": "LlamaTokenizer",
|
47 |
-
"truncation_side": "right",
|
48 |
"unk_token": "<unk>",
|
49 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": false,
|
3 |
"add_eos_token": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"model_max_length": 4096,
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"unk_token": "<unk>",
|
6 |
+
"bos_token": "<|startoftext|>",
|
7 |
+
"eos_token": "<|endoftext|>",
|
8 |
+
"pad_token": "<unk>",
|
9 |
+
"sp_model_kwargs": {},
|
10 |
+
"clean_up_tokenization_spaces": false,
|
11 |
+
"legacy": true,
|
12 |
+
"tokenizer_class": "LlamaTokenizer"
|
13 |
}
|