Commit
•
71e9d7b
1
Parent(s):
8a32f08
Delete tokenizer_config.json
Browse files- tokenizer_config.json +0 -77
tokenizer_config.json
DELETED
|
@@ -1,77 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_bos_token": true,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": null,
|
| 5 |
-
"added_tokens_decoder": {
|
| 6 |
-
"0": {
|
| 7 |
-
"content": "<unk>",
|
| 8 |
-
"lstrip": false,
|
| 9 |
-
"normalized": false,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false,
|
| 12 |
-
"special": true
|
| 13 |
-
},
|
| 14 |
-
"1": {
|
| 15 |
-
"content": "<s>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": false,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false,
|
| 20 |
-
"special": true
|
| 21 |
-
},
|
| 22 |
-
"2": {
|
| 23 |
-
"content": "</s>",
|
| 24 |
-
"lstrip": false,
|
| 25 |
-
"normalized": false,
|
| 26 |
-
"rstrip": false,
|
| 27 |
-
"single_word": false,
|
| 28 |
-
"special": true
|
| 29 |
-
},
|
| 30 |
-
"32000": {
|
| 31 |
-
"content": "<fake_token_around_image>",
|
| 32 |
-
"lstrip": false,
|
| 33 |
-
"normalized": false,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false,
|
| 36 |
-
"special": true
|
| 37 |
-
},
|
| 38 |
-
"32001": {
|
| 39 |
-
"content": "<image>",
|
| 40 |
-
"lstrip": false,
|
| 41 |
-
"normalized": false,
|
| 42 |
-
"rstrip": false,
|
| 43 |
-
"single_word": false,
|
| 44 |
-
"special": true
|
| 45 |
-
},
|
| 46 |
-
"32002": {
|
| 47 |
-
"content": "<end_of_utterance>",
|
| 48 |
-
"lstrip": false,
|
| 49 |
-
"normalized": false,
|
| 50 |
-
"rstrip": false,
|
| 51 |
-
"single_word": false,
|
| 52 |
-
"special": true
|
| 53 |
-
}
|
| 54 |
-
},
|
| 55 |
-
"additional_special_tokens": [
|
| 56 |
-
"<fake_token_around_image>",
|
| 57 |
-
"<image>",
|
| 58 |
-
"<end_of_utterance>"
|
| 59 |
-
],
|
| 60 |
-
"bos_token": "<s>",
|
| 61 |
-
"clean_up_tokenization_spaces": false,
|
| 62 |
-
"do_image_splitting": false,
|
| 63 |
-
"eos_token": "</s>",
|
| 64 |
-
"legacy": false,
|
| 65 |
-
"max_length": null,
|
| 66 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 67 |
-
"pad_to_multiple_of": null,
|
| 68 |
-
"pad_token": "<unk>",
|
| 69 |
-
"pad_token_type_id": 0,
|
| 70 |
-
"padding_side": "left",
|
| 71 |
-
"processor_class": "Idefics2Processor",
|
| 72 |
-
"sp_model_kwargs": {},
|
| 73 |
-
"spaces_between_special_tokens": false,
|
| 74 |
-
"tokenizer_class": "LlamaTokenizer",
|
| 75 |
-
"unk_token": "<unk>",
|
| 76 |
-
"use_default_system_prompt": true
|
| 77 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|