Upload processor
Browse files- added_tokens.json +130 -0
- chat_template.json +3 -0
- merges.txt +0 -0
- preprocessor_config.json +28 -0
- processor_config.json +4 -0
- special_tokens_map.json +53 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1183 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<end_of_utterance>": 49279,
|
| 3 |
+
"<fake_token_around_image>": 49189,
|
| 4 |
+
"<global-img>": 49152,
|
| 5 |
+
"<image>": 49190,
|
| 6 |
+
"<row_1_col_1>": 49153,
|
| 7 |
+
"<row_1_col_2>": 49154,
|
| 8 |
+
"<row_1_col_3>": 49155,
|
| 9 |
+
"<row_1_col_4>": 49156,
|
| 10 |
+
"<row_1_col_5>": 49157,
|
| 11 |
+
"<row_1_col_6>": 49158,
|
| 12 |
+
"<row_2_col_1>": 49159,
|
| 13 |
+
"<row_2_col_2>": 49160,
|
| 14 |
+
"<row_2_col_3>": 49161,
|
| 15 |
+
"<row_2_col_4>": 49162,
|
| 16 |
+
"<row_2_col_5>": 49163,
|
| 17 |
+
"<row_2_col_6>": 49164,
|
| 18 |
+
"<row_3_col_1>": 49165,
|
| 19 |
+
"<row_3_col_2>": 49166,
|
| 20 |
+
"<row_3_col_3>": 49167,
|
| 21 |
+
"<row_3_col_4>": 49168,
|
| 22 |
+
"<row_3_col_5>": 49169,
|
| 23 |
+
"<row_3_col_6>": 49170,
|
| 24 |
+
"<row_4_col_1>": 49171,
|
| 25 |
+
"<row_4_col_2>": 49172,
|
| 26 |
+
"<row_4_col_3>": 49173,
|
| 27 |
+
"<row_4_col_4>": 49174,
|
| 28 |
+
"<row_4_col_5>": 49175,
|
| 29 |
+
"<row_4_col_6>": 49176,
|
| 30 |
+
"<row_5_col_1>": 49177,
|
| 31 |
+
"<row_5_col_2>": 49178,
|
| 32 |
+
"<row_5_col_3>": 49179,
|
| 33 |
+
"<row_5_col_4>": 49180,
|
| 34 |
+
"<row_5_col_5>": 49181,
|
| 35 |
+
"<row_5_col_6>": 49182,
|
| 36 |
+
"<row_6_col_1>": 49183,
|
| 37 |
+
"<row_6_col_2>": 49184,
|
| 38 |
+
"<row_6_col_3>": 49185,
|
| 39 |
+
"<row_6_col_4>": 49186,
|
| 40 |
+
"<row_6_col_5>": 49187,
|
| 41 |
+
"<row_6_col_6>": 49188,
|
| 42 |
+
"<|reserved_special_token_0|>": 49191,
|
| 43 |
+
"<|reserved_special_token_10|>": 49201,
|
| 44 |
+
"<|reserved_special_token_11|>": 49202,
|
| 45 |
+
"<|reserved_special_token_12|>": 49203,
|
| 46 |
+
"<|reserved_special_token_13|>": 49204,
|
| 47 |
+
"<|reserved_special_token_14|>": 49205,
|
| 48 |
+
"<|reserved_special_token_15|>": 49206,
|
| 49 |
+
"<|reserved_special_token_16|>": 49207,
|
| 50 |
+
"<|reserved_special_token_17|>": 49208,
|
| 51 |
+
"<|reserved_special_token_18|>": 49209,
|
| 52 |
+
"<|reserved_special_token_19|>": 49210,
|
| 53 |
+
"<|reserved_special_token_1|>": 49192,
|
| 54 |
+
"<|reserved_special_token_20|>": 49211,
|
| 55 |
+
"<|reserved_special_token_21|>": 49212,
|
| 56 |
+
"<|reserved_special_token_22|>": 49213,
|
| 57 |
+
"<|reserved_special_token_23|>": 49214,
|
| 58 |
+
"<|reserved_special_token_24|>": 49215,
|
| 59 |
+
"<|reserved_special_token_25|>": 49216,
|
| 60 |
+
"<|reserved_special_token_26|>": 49217,
|
| 61 |
+
"<|reserved_special_token_27|>": 49218,
|
| 62 |
+
"<|reserved_special_token_28|>": 49219,
|
| 63 |
+
"<|reserved_special_token_29|>": 49220,
|
| 64 |
+
"<|reserved_special_token_2|>": 49193,
|
| 65 |
+
"<|reserved_special_token_30|>": 49221,
|
| 66 |
+
"<|reserved_special_token_31|>": 49222,
|
| 67 |
+
"<|reserved_special_token_32|>": 49223,
|
| 68 |
+
"<|reserved_special_token_33|>": 49224,
|
| 69 |
+
"<|reserved_special_token_34|>": 49225,
|
| 70 |
+
"<|reserved_special_token_35|>": 49226,
|
| 71 |
+
"<|reserved_special_token_36|>": 49227,
|
| 72 |
+
"<|reserved_special_token_37|>": 49228,
|
| 73 |
+
"<|reserved_special_token_38|>": 49229,
|
| 74 |
+
"<|reserved_special_token_39|>": 49230,
|
| 75 |
+
"<|reserved_special_token_3|>": 49194,
|
| 76 |
+
"<|reserved_special_token_40|>": 49231,
|
| 77 |
+
"<|reserved_special_token_41|>": 49232,
|
| 78 |
+
"<|reserved_special_token_42|>": 49233,
|
| 79 |
+
"<|reserved_special_token_43|>": 49234,
|
| 80 |
+
"<|reserved_special_token_44|>": 49235,
|
| 81 |
+
"<|reserved_special_token_45|>": 49236,
|
| 82 |
+
"<|reserved_special_token_46|>": 49237,
|
| 83 |
+
"<|reserved_special_token_47|>": 49238,
|
| 84 |
+
"<|reserved_special_token_48|>": 49239,
|
| 85 |
+
"<|reserved_special_token_49|>": 49240,
|
| 86 |
+
"<|reserved_special_token_4|>": 49195,
|
| 87 |
+
"<|reserved_special_token_50|>": 49241,
|
| 88 |
+
"<|reserved_special_token_51|>": 49242,
|
| 89 |
+
"<|reserved_special_token_52|>": 49243,
|
| 90 |
+
"<|reserved_special_token_53|>": 49244,
|
| 91 |
+
"<|reserved_special_token_54|>": 49245,
|
| 92 |
+
"<|reserved_special_token_55|>": 49246,
|
| 93 |
+
"<|reserved_special_token_56|>": 49247,
|
| 94 |
+
"<|reserved_special_token_57|>": 49248,
|
| 95 |
+
"<|reserved_special_token_58|>": 49249,
|
| 96 |
+
"<|reserved_special_token_59|>": 49250,
|
| 97 |
+
"<|reserved_special_token_5|>": 49196,
|
| 98 |
+
"<|reserved_special_token_60|>": 49251,
|
| 99 |
+
"<|reserved_special_token_61|>": 49252,
|
| 100 |
+
"<|reserved_special_token_62|>": 49253,
|
| 101 |
+
"<|reserved_special_token_63|>": 49254,
|
| 102 |
+
"<|reserved_special_token_64|>": 49255,
|
| 103 |
+
"<|reserved_special_token_65|>": 49256,
|
| 104 |
+
"<|reserved_special_token_66|>": 49257,
|
| 105 |
+
"<|reserved_special_token_67|>": 49258,
|
| 106 |
+
"<|reserved_special_token_68|>": 49259,
|
| 107 |
+
"<|reserved_special_token_69|>": 49260,
|
| 108 |
+
"<|reserved_special_token_6|>": 49197,
|
| 109 |
+
"<|reserved_special_token_70|>": 49261,
|
| 110 |
+
"<|reserved_special_token_71|>": 49262,
|
| 111 |
+
"<|reserved_special_token_72|>": 49263,
|
| 112 |
+
"<|reserved_special_token_73|>": 49264,
|
| 113 |
+
"<|reserved_special_token_74|>": 49265,
|
| 114 |
+
"<|reserved_special_token_75|>": 49266,
|
| 115 |
+
"<|reserved_special_token_76|>": 49267,
|
| 116 |
+
"<|reserved_special_token_77|>": 49268,
|
| 117 |
+
"<|reserved_special_token_78|>": 49269,
|
| 118 |
+
"<|reserved_special_token_79|>": 49270,
|
| 119 |
+
"<|reserved_special_token_7|>": 49198,
|
| 120 |
+
"<|reserved_special_token_80|>": 49271,
|
| 121 |
+
"<|reserved_special_token_81|>": 49272,
|
| 122 |
+
"<|reserved_special_token_82|>": 49273,
|
| 123 |
+
"<|reserved_special_token_83|>": 49274,
|
| 124 |
+
"<|reserved_special_token_84|>": 49275,
|
| 125 |
+
"<|reserved_special_token_85|>": 49276,
|
| 126 |
+
"<|reserved_special_token_86|>": 49277,
|
| 127 |
+
"<|reserved_special_token_87|>": 49278,
|
| 128 |
+
"<|reserved_special_token_8|>": 49199,
|
| 129 |
+
"<|reserved_special_token_9|>": 49200
|
| 130 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "<|im_start|>{% for message in messages %}{{message['role'].capitalize()}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
|
| 3 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_image_splitting": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_pad": true,
|
| 6 |
+
"do_rescale": true,
|
| 7 |
+
"do_resize": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "Idefics3ImageProcessor",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"max_image_size": {
|
| 20 |
+
"longest_edge": 384
|
| 21 |
+
},
|
| 22 |
+
"processor_class": "Idefics3Processor",
|
| 23 |
+
"resample": 1,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"longest_edge": 1536
|
| 27 |
+
}
|
| 28 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_seq_len": 81,
|
| 3 |
+
"processor_class": "Idefics3Processor"
|
| 4 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<fake_token_around_image>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<image>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<end_of_utterance>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
],
|
| 25 |
+
"bos_token": {
|
| 26 |
+
"content": "<|im_start|>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
"eos_token": {
|
| 33 |
+
"content": "<end_of_utterance>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
},
|
| 39 |
+
"pad_token": {
|
| 40 |
+
"content": "<|im_end|>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
"unk_token": {
|
| 47 |
+
"content": "<|endoftext|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false
|
| 52 |
+
}
|
| 53 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,1183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<repo_name>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<reponame>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<file_sep>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<filename>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<gh_stars>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_start>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_comment>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<issue_closed>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_start>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_text>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_code>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<jupyter_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<jupyter_script>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<empty_output>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"49152": {
|
| 141 |
+
"content": "<global-img>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"49153": {
|
| 149 |
+
"content": "<row_1_col_1>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"49154": {
|
| 157 |
+
"content": "<row_1_col_2>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"49155": {
|
| 165 |
+
"content": "<row_1_col_3>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"49156": {
|
| 173 |
+
"content": "<row_1_col_4>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"49157": {
|
| 181 |
+
"content": "<row_1_col_5>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"49158": {
|
| 189 |
+
"content": "<row_1_col_6>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"49159": {
|
| 197 |
+
"content": "<row_2_col_1>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"49160": {
|
| 205 |
+
"content": "<row_2_col_2>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"49161": {
|
| 213 |
+
"content": "<row_2_col_3>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"49162": {
|
| 221 |
+
"content": "<row_2_col_4>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"49163": {
|
| 229 |
+
"content": "<row_2_col_5>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"49164": {
|
| 237 |
+
"content": "<row_2_col_6>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"49165": {
|
| 245 |
+
"content": "<row_3_col_1>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"49166": {
|
| 253 |
+
"content": "<row_3_col_2>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"49167": {
|
| 261 |
+
"content": "<row_3_col_3>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"49168": {
|
| 269 |
+
"content": "<row_3_col_4>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"49169": {
|
| 277 |
+
"content": "<row_3_col_5>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"49170": {
|
| 285 |
+
"content": "<row_3_col_6>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"49171": {
|
| 293 |
+
"content": "<row_4_col_1>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"49172": {
|
| 301 |
+
"content": "<row_4_col_2>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"49173": {
|
| 309 |
+
"content": "<row_4_col_3>",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"49174": {
|
| 317 |
+
"content": "<row_4_col_4>",
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"49175": {
|
| 325 |
+
"content": "<row_4_col_5>",
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"49176": {
|
| 333 |
+
"content": "<row_4_col_6>",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"49177": {
|
| 341 |
+
"content": "<row_5_col_1>",
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"49178": {
|
| 349 |
+
"content": "<row_5_col_2>",
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"49179": {
|
| 357 |
+
"content": "<row_5_col_3>",
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"49180": {
|
| 365 |
+
"content": "<row_5_col_4>",
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"49181": {
|
| 373 |
+
"content": "<row_5_col_5>",
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"49182": {
|
| 381 |
+
"content": "<row_5_col_6>",
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"49183": {
|
| 389 |
+
"content": "<row_6_col_1>",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"49184": {
|
| 397 |
+
"content": "<row_6_col_2>",
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"49185": {
|
| 405 |
+
"content": "<row_6_col_3>",
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"49186": {
|
| 413 |
+
"content": "<row_6_col_4>",
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"49187": {
|
| 421 |
+
"content": "<row_6_col_5>",
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"49188": {
|
| 429 |
+
"content": "<row_6_col_6>",
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"49189": {
|
| 437 |
+
"content": "<fake_token_around_image>",
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": false,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"49190": {
|
| 445 |
+
"content": "<image>",
|
| 446 |
+
"lstrip": false,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"49191": {
|
| 453 |
+
"content": "<|reserved_special_token_0|>",
|
| 454 |
+
"lstrip": false,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"49192": {
|
| 461 |
+
"content": "<|reserved_special_token_1|>",
|
| 462 |
+
"lstrip": false,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": false,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"49193": {
|
| 469 |
+
"content": "<|reserved_special_token_2|>",
|
| 470 |
+
"lstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": false,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"49194": {
|
| 477 |
+
"content": "<|reserved_special_token_3|>",
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": false,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"49195": {
|
| 485 |
+
"content": "<|reserved_special_token_4|>",
|
| 486 |
+
"lstrip": false,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"49196": {
|
| 493 |
+
"content": "<|reserved_special_token_5|>",
|
| 494 |
+
"lstrip": false,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": false,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"49197": {
|
| 501 |
+
"content": "<|reserved_special_token_6|>",
|
| 502 |
+
"lstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"49198": {
|
| 509 |
+
"content": "<|reserved_special_token_7|>",
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"49199": {
|
| 517 |
+
"content": "<|reserved_special_token_8|>",
|
| 518 |
+
"lstrip": false,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"49200": {
|
| 525 |
+
"content": "<|reserved_special_token_9|>",
|
| 526 |
+
"lstrip": false,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": false,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"49201": {
|
| 533 |
+
"content": "<|reserved_special_token_10|>",
|
| 534 |
+
"lstrip": false,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": false,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"49202": {
|
| 541 |
+
"content": "<|reserved_special_token_11|>",
|
| 542 |
+
"lstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": false,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"49203": {
|
| 549 |
+
"content": "<|reserved_special_token_12|>",
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": false,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"49204": {
|
| 557 |
+
"content": "<|reserved_special_token_13|>",
|
| 558 |
+
"lstrip": false,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"49205": {
|
| 565 |
+
"content": "<|reserved_special_token_14|>",
|
| 566 |
+
"lstrip": false,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"49206": {
|
| 573 |
+
"content": "<|reserved_special_token_15|>",
|
| 574 |
+
"lstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"49207": {
|
| 581 |
+
"content": "<|reserved_special_token_16|>",
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": false,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"49208": {
|
| 589 |
+
"content": "<|reserved_special_token_17|>",
|
| 590 |
+
"lstrip": false,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"49209": {
|
| 597 |
+
"content": "<|reserved_special_token_18|>",
|
| 598 |
+
"lstrip": false,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": false,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"49210": {
|
| 605 |
+
"content": "<|reserved_special_token_19|>",
|
| 606 |
+
"lstrip": false,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": false,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"49211": {
|
| 613 |
+
"content": "<|reserved_special_token_20|>",
|
| 614 |
+
"lstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"49212": {
|
| 621 |
+
"content": "<|reserved_special_token_21|>",
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"49213": {
|
| 629 |
+
"content": "<|reserved_special_token_22|>",
|
| 630 |
+
"lstrip": false,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"49214": {
|
| 637 |
+
"content": "<|reserved_special_token_23|>",
|
| 638 |
+
"lstrip": false,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": false,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"49215": {
|
| 645 |
+
"content": "<|reserved_special_token_24|>",
|
| 646 |
+
"lstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"49216": {
|
| 653 |
+
"content": "<|reserved_special_token_25|>",
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": false,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"49217": {
|
| 661 |
+
"content": "<|reserved_special_token_26|>",
|
| 662 |
+
"lstrip": false,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"49218": {
|
| 669 |
+
"content": "<|reserved_special_token_27|>",
|
| 670 |
+
"lstrip": false,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"49219": {
|
| 677 |
+
"content": "<|reserved_special_token_28|>",
|
| 678 |
+
"lstrip": false,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"49220": {
|
| 685 |
+
"content": "<|reserved_special_token_29|>",
|
| 686 |
+
"lstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": false,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"49221": {
|
| 693 |
+
"content": "<|reserved_special_token_30|>",
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": false,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"49222": {
|
| 701 |
+
"content": "<|reserved_special_token_31|>",
|
| 702 |
+
"lstrip": false,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"49223": {
|
| 709 |
+
"content": "<|reserved_special_token_32|>",
|
| 710 |
+
"lstrip": false,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": false,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"49224": {
|
| 717 |
+
"content": "<|reserved_special_token_33|>",
|
| 718 |
+
"lstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"49225": {
|
| 725 |
+
"content": "<|reserved_special_token_34|>",
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": false,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"49226": {
|
| 733 |
+
"content": "<|reserved_special_token_35|>",
|
| 734 |
+
"lstrip": false,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"49227": {
|
| 741 |
+
"content": "<|reserved_special_token_36|>",
|
| 742 |
+
"lstrip": false,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": false,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"49228": {
|
| 749 |
+
"content": "<|reserved_special_token_37|>",
|
| 750 |
+
"lstrip": false,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": false,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"49229": {
|
| 757 |
+
"content": "<|reserved_special_token_38|>",
|
| 758 |
+
"lstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": false,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"49230": {
|
| 765 |
+
"content": "<|reserved_special_token_39|>",
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": false,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"49231": {
|
| 773 |
+
"content": "<|reserved_special_token_40|>",
|
| 774 |
+
"lstrip": false,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"49232": {
|
| 781 |
+
"content": "<|reserved_special_token_41|>",
|
| 782 |
+
"lstrip": false,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": false,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"49233": {
|
| 789 |
+
"content": "<|reserved_special_token_42|>",
|
| 790 |
+
"lstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"49234": {
|
| 797 |
+
"content": "<|reserved_special_token_43|>",
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"49235": {
|
| 805 |
+
"content": "<|reserved_special_token_44|>",
|
| 806 |
+
"lstrip": false,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"49236": {
|
| 813 |
+
"content": "<|reserved_special_token_45|>",
|
| 814 |
+
"lstrip": false,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"49237": {
|
| 821 |
+
"content": "<|reserved_special_token_46|>",
|
| 822 |
+
"lstrip": false,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": false,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": true
|
| 827 |
+
},
|
| 828 |
+
"49238": {
|
| 829 |
+
"content": "<|reserved_special_token_47|>",
|
| 830 |
+
"lstrip": false,
|
| 831 |
+
"normalized": false,
|
| 832 |
+
"rstrip": false,
|
| 833 |
+
"single_word": false,
|
| 834 |
+
"special": true
|
| 835 |
+
},
|
| 836 |
+
"49239": {
|
| 837 |
+
"content": "<|reserved_special_token_48|>",
|
| 838 |
+
"lstrip": false,
|
| 839 |
+
"normalized": false,
|
| 840 |
+
"rstrip": false,
|
| 841 |
+
"single_word": false,
|
| 842 |
+
"special": true
|
| 843 |
+
},
|
| 844 |
+
"49240": {
|
| 845 |
+
"content": "<|reserved_special_token_49|>",
|
| 846 |
+
"lstrip": false,
|
| 847 |
+
"normalized": false,
|
| 848 |
+
"rstrip": false,
|
| 849 |
+
"single_word": false,
|
| 850 |
+
"special": true
|
| 851 |
+
},
|
| 852 |
+
"49241": {
|
| 853 |
+
"content": "<|reserved_special_token_50|>",
|
| 854 |
+
"lstrip": false,
|
| 855 |
+
"normalized": false,
|
| 856 |
+
"rstrip": false,
|
| 857 |
+
"single_word": false,
|
| 858 |
+
"special": true
|
| 859 |
+
},
|
| 860 |
+
"49242": {
|
| 861 |
+
"content": "<|reserved_special_token_51|>",
|
| 862 |
+
"lstrip": false,
|
| 863 |
+
"normalized": false,
|
| 864 |
+
"rstrip": false,
|
| 865 |
+
"single_word": false,
|
| 866 |
+
"special": true
|
| 867 |
+
},
|
| 868 |
+
"49243": {
|
| 869 |
+
"content": "<|reserved_special_token_52|>",
|
| 870 |
+
"lstrip": false,
|
| 871 |
+
"normalized": false,
|
| 872 |
+
"rstrip": false,
|
| 873 |
+
"single_word": false,
|
| 874 |
+
"special": true
|
| 875 |
+
},
|
| 876 |
+
"49244": {
|
| 877 |
+
"content": "<|reserved_special_token_53|>",
|
| 878 |
+
"lstrip": false,
|
| 879 |
+
"normalized": false,
|
| 880 |
+
"rstrip": false,
|
| 881 |
+
"single_word": false,
|
| 882 |
+
"special": true
|
| 883 |
+
},
|
| 884 |
+
"49245": {
|
| 885 |
+
"content": "<|reserved_special_token_54|>",
|
| 886 |
+
"lstrip": false,
|
| 887 |
+
"normalized": false,
|
| 888 |
+
"rstrip": false,
|
| 889 |
+
"single_word": false,
|
| 890 |
+
"special": true
|
| 891 |
+
},
|
| 892 |
+
"49246": {
|
| 893 |
+
"content": "<|reserved_special_token_55|>",
|
| 894 |
+
"lstrip": false,
|
| 895 |
+
"normalized": false,
|
| 896 |
+
"rstrip": false,
|
| 897 |
+
"single_word": false,
|
| 898 |
+
"special": true
|
| 899 |
+
},
|
| 900 |
+
"49247": {
|
| 901 |
+
"content": "<|reserved_special_token_56|>",
|
| 902 |
+
"lstrip": false,
|
| 903 |
+
"normalized": false,
|
| 904 |
+
"rstrip": false,
|
| 905 |
+
"single_word": false,
|
| 906 |
+
"special": true
|
| 907 |
+
},
|
| 908 |
+
"49248": {
|
| 909 |
+
"content": "<|reserved_special_token_57|>",
|
| 910 |
+
"lstrip": false,
|
| 911 |
+
"normalized": false,
|
| 912 |
+
"rstrip": false,
|
| 913 |
+
"single_word": false,
|
| 914 |
+
"special": true
|
| 915 |
+
},
|
| 916 |
+
"49249": {
|
| 917 |
+
"content": "<|reserved_special_token_58|>",
|
| 918 |
+
"lstrip": false,
|
| 919 |
+
"normalized": false,
|
| 920 |
+
"rstrip": false,
|
| 921 |
+
"single_word": false,
|
| 922 |
+
"special": true
|
| 923 |
+
},
|
| 924 |
+
"49250": {
|
| 925 |
+
"content": "<|reserved_special_token_59|>",
|
| 926 |
+
"lstrip": false,
|
| 927 |
+
"normalized": false,
|
| 928 |
+
"rstrip": false,
|
| 929 |
+
"single_word": false,
|
| 930 |
+
"special": true
|
| 931 |
+
},
|
| 932 |
+
"49251": {
|
| 933 |
+
"content": "<|reserved_special_token_60|>",
|
| 934 |
+
"lstrip": false,
|
| 935 |
+
"normalized": false,
|
| 936 |
+
"rstrip": false,
|
| 937 |
+
"single_word": false,
|
| 938 |
+
"special": true
|
| 939 |
+
},
|
| 940 |
+
"49252": {
|
| 941 |
+
"content": "<|reserved_special_token_61|>",
|
| 942 |
+
"lstrip": false,
|
| 943 |
+
"normalized": false,
|
| 944 |
+
"rstrip": false,
|
| 945 |
+
"single_word": false,
|
| 946 |
+
"special": true
|
| 947 |
+
},
|
| 948 |
+
"49253": {
|
| 949 |
+
"content": "<|reserved_special_token_62|>",
|
| 950 |
+
"lstrip": false,
|
| 951 |
+
"normalized": false,
|
| 952 |
+
"rstrip": false,
|
| 953 |
+
"single_word": false,
|
| 954 |
+
"special": true
|
| 955 |
+
},
|
| 956 |
+
"49254": {
|
| 957 |
+
"content": "<|reserved_special_token_63|>",
|
| 958 |
+
"lstrip": false,
|
| 959 |
+
"normalized": false,
|
| 960 |
+
"rstrip": false,
|
| 961 |
+
"single_word": false,
|
| 962 |
+
"special": true
|
| 963 |
+
},
|
| 964 |
+
"49255": {
|
| 965 |
+
"content": "<|reserved_special_token_64|>",
|
| 966 |
+
"lstrip": false,
|
| 967 |
+
"normalized": false,
|
| 968 |
+
"rstrip": false,
|
| 969 |
+
"single_word": false,
|
| 970 |
+
"special": true
|
| 971 |
+
},
|
| 972 |
+
"49256": {
|
| 973 |
+
"content": "<|reserved_special_token_65|>",
|
| 974 |
+
"lstrip": false,
|
| 975 |
+
"normalized": false,
|
| 976 |
+
"rstrip": false,
|
| 977 |
+
"single_word": false,
|
| 978 |
+
"special": true
|
| 979 |
+
},
|
| 980 |
+
"49257": {
|
| 981 |
+
"content": "<|reserved_special_token_66|>",
|
| 982 |
+
"lstrip": false,
|
| 983 |
+
"normalized": false,
|
| 984 |
+
"rstrip": false,
|
| 985 |
+
"single_word": false,
|
| 986 |
+
"special": true
|
| 987 |
+
},
|
| 988 |
+
"49258": {
|
| 989 |
+
"content": "<|reserved_special_token_67|>",
|
| 990 |
+
"lstrip": false,
|
| 991 |
+
"normalized": false,
|
| 992 |
+
"rstrip": false,
|
| 993 |
+
"single_word": false,
|
| 994 |
+
"special": true
|
| 995 |
+
},
|
| 996 |
+
"49259": {
|
| 997 |
+
"content": "<|reserved_special_token_68|>",
|
| 998 |
+
"lstrip": false,
|
| 999 |
+
"normalized": false,
|
| 1000 |
+
"rstrip": false,
|
| 1001 |
+
"single_word": false,
|
| 1002 |
+
"special": true
|
| 1003 |
+
},
|
| 1004 |
+
"49260": {
|
| 1005 |
+
"content": "<|reserved_special_token_69|>",
|
| 1006 |
+
"lstrip": false,
|
| 1007 |
+
"normalized": false,
|
| 1008 |
+
"rstrip": false,
|
| 1009 |
+
"single_word": false,
|
| 1010 |
+
"special": true
|
| 1011 |
+
},
|
| 1012 |
+
"49261": {
|
| 1013 |
+
"content": "<|reserved_special_token_70|>",
|
| 1014 |
+
"lstrip": false,
|
| 1015 |
+
"normalized": false,
|
| 1016 |
+
"rstrip": false,
|
| 1017 |
+
"single_word": false,
|
| 1018 |
+
"special": true
|
| 1019 |
+
},
|
| 1020 |
+
"49262": {
|
| 1021 |
+
"content": "<|reserved_special_token_71|>",
|
| 1022 |
+
"lstrip": false,
|
| 1023 |
+
"normalized": false,
|
| 1024 |
+
"rstrip": false,
|
| 1025 |
+
"single_word": false,
|
| 1026 |
+
"special": true
|
| 1027 |
+
},
|
| 1028 |
+
"49263": {
|
| 1029 |
+
"content": "<|reserved_special_token_72|>",
|
| 1030 |
+
"lstrip": false,
|
| 1031 |
+
"normalized": false,
|
| 1032 |
+
"rstrip": false,
|
| 1033 |
+
"single_word": false,
|
| 1034 |
+
"special": true
|
| 1035 |
+
},
|
| 1036 |
+
"49264": {
|
| 1037 |
+
"content": "<|reserved_special_token_73|>",
|
| 1038 |
+
"lstrip": false,
|
| 1039 |
+
"normalized": false,
|
| 1040 |
+
"rstrip": false,
|
| 1041 |
+
"single_word": false,
|
| 1042 |
+
"special": true
|
| 1043 |
+
},
|
| 1044 |
+
"49265": {
|
| 1045 |
+
"content": "<|reserved_special_token_74|>",
|
| 1046 |
+
"lstrip": false,
|
| 1047 |
+
"normalized": false,
|
| 1048 |
+
"rstrip": false,
|
| 1049 |
+
"single_word": false,
|
| 1050 |
+
"special": true
|
| 1051 |
+
},
|
| 1052 |
+
"49266": {
|
| 1053 |
+
"content": "<|reserved_special_token_75|>",
|
| 1054 |
+
"lstrip": false,
|
| 1055 |
+
"normalized": false,
|
| 1056 |
+
"rstrip": false,
|
| 1057 |
+
"single_word": false,
|
| 1058 |
+
"special": true
|
| 1059 |
+
},
|
| 1060 |
+
"49267": {
|
| 1061 |
+
"content": "<|reserved_special_token_76|>",
|
| 1062 |
+
"lstrip": false,
|
| 1063 |
+
"normalized": false,
|
| 1064 |
+
"rstrip": false,
|
| 1065 |
+
"single_word": false,
|
| 1066 |
+
"special": true
|
| 1067 |
+
},
|
| 1068 |
+
"49268": {
|
| 1069 |
+
"content": "<|reserved_special_token_77|>",
|
| 1070 |
+
"lstrip": false,
|
| 1071 |
+
"normalized": false,
|
| 1072 |
+
"rstrip": false,
|
| 1073 |
+
"single_word": false,
|
| 1074 |
+
"special": true
|
| 1075 |
+
},
|
| 1076 |
+
"49269": {
|
| 1077 |
+
"content": "<|reserved_special_token_78|>",
|
| 1078 |
+
"lstrip": false,
|
| 1079 |
+
"normalized": false,
|
| 1080 |
+
"rstrip": false,
|
| 1081 |
+
"single_word": false,
|
| 1082 |
+
"special": true
|
| 1083 |
+
},
|
| 1084 |
+
"49270": {
|
| 1085 |
+
"content": "<|reserved_special_token_79|>",
|
| 1086 |
+
"lstrip": false,
|
| 1087 |
+
"normalized": false,
|
| 1088 |
+
"rstrip": false,
|
| 1089 |
+
"single_word": false,
|
| 1090 |
+
"special": true
|
| 1091 |
+
},
|
| 1092 |
+
"49271": {
|
| 1093 |
+
"content": "<|reserved_special_token_80|>",
|
| 1094 |
+
"lstrip": false,
|
| 1095 |
+
"normalized": false,
|
| 1096 |
+
"rstrip": false,
|
| 1097 |
+
"single_word": false,
|
| 1098 |
+
"special": true
|
| 1099 |
+
},
|
| 1100 |
+
"49272": {
|
| 1101 |
+
"content": "<|reserved_special_token_81|>",
|
| 1102 |
+
"lstrip": false,
|
| 1103 |
+
"normalized": false,
|
| 1104 |
+
"rstrip": false,
|
| 1105 |
+
"single_word": false,
|
| 1106 |
+
"special": true
|
| 1107 |
+
},
|
| 1108 |
+
"49273": {
|
| 1109 |
+
"content": "<|reserved_special_token_82|>",
|
| 1110 |
+
"lstrip": false,
|
| 1111 |
+
"normalized": false,
|
| 1112 |
+
"rstrip": false,
|
| 1113 |
+
"single_word": false,
|
| 1114 |
+
"special": true
|
| 1115 |
+
},
|
| 1116 |
+
"49274": {
|
| 1117 |
+
"content": "<|reserved_special_token_83|>",
|
| 1118 |
+
"lstrip": false,
|
| 1119 |
+
"normalized": false,
|
| 1120 |
+
"rstrip": false,
|
| 1121 |
+
"single_word": false,
|
| 1122 |
+
"special": true
|
| 1123 |
+
},
|
| 1124 |
+
"49275": {
|
| 1125 |
+
"content": "<|reserved_special_token_84|>",
|
| 1126 |
+
"lstrip": false,
|
| 1127 |
+
"normalized": false,
|
| 1128 |
+
"rstrip": false,
|
| 1129 |
+
"single_word": false,
|
| 1130 |
+
"special": true
|
| 1131 |
+
},
|
| 1132 |
+
"49276": {
|
| 1133 |
+
"content": "<|reserved_special_token_85|>",
|
| 1134 |
+
"lstrip": false,
|
| 1135 |
+
"normalized": false,
|
| 1136 |
+
"rstrip": false,
|
| 1137 |
+
"single_word": false,
|
| 1138 |
+
"special": true
|
| 1139 |
+
},
|
| 1140 |
+
"49277": {
|
| 1141 |
+
"content": "<|reserved_special_token_86|>",
|
| 1142 |
+
"lstrip": false,
|
| 1143 |
+
"normalized": false,
|
| 1144 |
+
"rstrip": false,
|
| 1145 |
+
"single_word": false,
|
| 1146 |
+
"special": true
|
| 1147 |
+
},
|
| 1148 |
+
"49278": {
|
| 1149 |
+
"content": "<|reserved_special_token_87|>",
|
| 1150 |
+
"lstrip": false,
|
| 1151 |
+
"normalized": false,
|
| 1152 |
+
"rstrip": false,
|
| 1153 |
+
"single_word": false,
|
| 1154 |
+
"special": true
|
| 1155 |
+
},
|
| 1156 |
+
"49279": {
|
| 1157 |
+
"content": "<end_of_utterance>",
|
| 1158 |
+
"lstrip": false,
|
| 1159 |
+
"normalized": false,
|
| 1160 |
+
"rstrip": false,
|
| 1161 |
+
"single_word": false,
|
| 1162 |
+
"special": true
|
| 1163 |
+
}
|
| 1164 |
+
},
|
| 1165 |
+
"additional_special_tokens": [
|
| 1166 |
+
"<fake_token_around_image>",
|
| 1167 |
+
"<image>",
|
| 1168 |
+
"<end_of_utterance>"
|
| 1169 |
+
],
|
| 1170 |
+
"bos_token": "<|im_start|>",
|
| 1171 |
+
"chat_template": "<|im_start|>{% for message in messages %}{{message['role'].capitalize()}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
|
| 1172 |
+
"clean_up_tokenization_spaces": false,
|
| 1173 |
+
"eos_token": "<end_of_utterance>",
|
| 1174 |
+
"extra_special_tokens": {},
|
| 1175 |
+
"legacy": false,
|
| 1176 |
+
"model_max_length": 16384,
|
| 1177 |
+
"pad_token": "<|im_end|>",
|
| 1178 |
+
"processor_class": "Idefics3Processor",
|
| 1179 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 1180 |
+
"truncation_side": "left",
|
| 1181 |
+
"unk_token": "<|endoftext|>",
|
| 1182 |
+
"vocab_size": 49152
|
| 1183 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|