Upload 10 files
Browse files- added_tokens.json +4 -0
- config.json +31 -0
- generation_config.json +6 -0
- merges.txt +177 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +598 -0
- tokenizer_config.json +9 -0
- training_args.bin +3 -0
- vocab.json +1 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 329,
|
| 3 |
+
"<unk>": 330
|
| 4 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 329,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 512,
|
| 14 |
+
"n_head": 4,
|
| 15 |
+
"n_inner": 512,
|
| 16 |
+
"n_layer": 3,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.30.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 331
|
| 31 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 329,
|
| 5 |
+
"transformers_version": "4.30.2"
|
| 6 |
+
}
|
merges.txt
ADDED
|
@@ -0,0 +1,177 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#version: 0.2
|
| 2 |
+
à ¤
|
| 3 |
+
à ¥
|
| 4 |
+
à ¦
|
| 5 |
+
à ¨
|
| 6 |
+
â Ģ
|
| 7 |
+
à §
|
| 8 |
+
à ©
|
| 9 |
+
s >
|
| 10 |
+
< \
|
| 11 |
+
< p
|
| 12 |
+
< s>
|
| 13 |
+
a d
|
| 14 |
+
 °
|
| 15 |
+
 ²
|
| 16 |
+
à ¡
|
| 17 |
+
à ¨
|
| 18 |
+
à ©
|
| 19 |
+
à ·
|
| 20 |
+
à Ĺ
|
| 21 |
+
Ë ļ
|
| 22 |
+
â Ī
|
| 23 |
+
ठ¡
|
| 24 |
+
ठ¢
|
| 25 |
+
ठ£
|
| 26 |
+
ठ¤
|
| 27 |
+
ठ¥
|
| 28 |
+
ठ¦
|
| 29 |
+
ठ§
|
| 30 |
+
ठ¨
|
| 31 |
+
ठª
|
| 32 |
+
ठ«
|
| 33 |
+
ठ¬
|
| 34 |
+
ठ®
|
| 35 |
+
ठ¯
|
| 36 |
+
ठ°
|
| 37 |
+
ठ²
|
| 38 |
+
ठ³
|
| 39 |
+
ठµ
|
| 40 |
+
ठ¶
|
| 41 |
+
ठ·
|
| 42 |
+
ठ¸
|
| 43 |
+
ठ¹
|
| 44 |
+
ठ¼
|
| 45 |
+
ठ½
|
| 46 |
+
ठ¾
|
| 47 |
+
ठ¿
|
| 48 |
+
ठģ
|
| 49 |
+
ठĤ
|
| 50 |
+
ठĥ
|
| 51 |
+
ठħ
|
| 52 |
+
ठĨ
|
| 53 |
+
ठĩ
|
| 54 |
+
ठĪ
|
| 55 |
+
ठī
|
| 56 |
+
ठĬ
|
| 57 |
+
ठĭ
|
| 58 |
+
ठį
|
| 59 |
+
ठı
|
| 60 |
+
ठIJ
|
| 61 |
+
ठij
|
| 62 |
+
ठĵ
|
| 63 |
+
ठĶ
|
| 64 |
+
ठķ
|
| 65 |
+
ठĸ
|
| 66 |
+
ठĹ
|
| 67 |
+
ठĺ
|
| 68 |
+
ठĻ
|
| 69 |
+
ठļ
|
| 70 |
+
ठĽ
|
| 71 |
+
ठľ
|
| 72 |
+
ठĿ
|
| 73 |
+
ठŀ
|
| 74 |
+
ठŁ
|
| 75 |
+
ठł
|
| 76 |
+
ठŃ
|
| 77 |
+
ॠ¤
|
| 78 |
+
ॠ¥
|
| 79 |
+
ॠ¦
|
| 80 |
+
ॠ§
|
| 81 |
+
ॠ¨
|
| 82 |
+
ॠ©
|
| 83 |
+
ॠª
|
| 84 |
+
ॠ«
|
| 85 |
+
ॠ¬
|
| 86 |
+
ॠ®
|
| 87 |
+
ॠ¯
|
| 88 |
+
ॠĢ
|
| 89 |
+
ॠģ
|
| 90 |
+
ॠĤ
|
| 91 |
+
ॠĥ
|
| 92 |
+
ॠĦ
|
| 93 |
+
ॠħ
|
| 94 |
+
ॠĩ
|
| 95 |
+
ॠĪ
|
| 96 |
+
ॠī
|
| 97 |
+
ॠĬ
|
| 98 |
+
ॠĭ
|
| 99 |
+
ॠĮ
|
| 100 |
+
ॠį
|
| 101 |
+
ॠIJ
|
| 102 |
+
ॠĺ
|
| 103 |
+
ॠĻ
|
| 104 |
+
ॠļ
|
| 105 |
+
ॠĽ
|
| 106 |
+
ॠľ
|
| 107 |
+
ॠĿ
|
| 108 |
+
ॠŀ
|
| 109 |
+
ॠŁ
|
| 110 |
+
ॠł
|
| 111 |
+
ॠŃ
|
| 112 |
+
ঠ¤
|
| 113 |
+
ঠ¥
|
| 114 |
+
ঠ¨
|
| 115 |
+
ঠª
|
| 116 |
+
ঠ¬
|
| 117 |
+
ঠ®
|
| 118 |
+
ঠ¯
|
| 119 |
+
ঠ²
|
| 120 |
+
ঠ¸
|
| 121 |
+
ঠ¹
|
| 122 |
+
ঠ¼
|
| 123 |
+
ঠ¾
|
| 124 |
+
ঠ¿
|
| 125 |
+
ঠĨ
|
| 126 |
+
ঠĩ
|
| 127 |
+
ঠı
|
| 128 |
+
ঠķ
|
| 129 |
+
ঠĹ
|
| 130 |
+
ঠļ
|
| 131 |
+
ঠĽ
|
| 132 |
+
ঠľ
|
| 133 |
+
ঠł
|
| 134 |
+
ਠ¤
|
| 135 |
+
ਠ¦
|
| 136 |
+
ਠ¨
|
| 137 |
+
ਠª
|
| 138 |
+
ਠ¬
|
| 139 |
+
ਠ®
|
| 140 |
+
ਠ²
|
| 141 |
+
ਠµ
|
| 142 |
+
ਠ¶
|
| 143 |
+
ਠ¸
|
| 144 |
+
ਠ¹
|
| 145 |
+
ਠ¼
|
| 146 |
+
ਠ¾
|
| 147 |
+
ਠ¿
|
| 148 |
+
ਠħ
|
| 149 |
+
ਠĨ
|
| 150 |
+
ਠī
|
| 151 |
+
ਠķ
|
| 152 |
+
ਠĸ
|
| 153 |
+
ਠļ
|
| 154 |
+
âĢ ¦
|
| 155 |
+
âĢ Į
|
| 156 |
+
âĢ į
|
| 157 |
+
âĢ ĵ
|
| 158 |
+
âĢ ĺ
|
| 159 |
+
âĢ Ļ
|
| 160 |
+
âĢ ľ
|
| 161 |
+
âĢ Ŀ
|
| 162 |
+
à§ °
|
| 163 |
+
à§ ±
|
| 164 |
+
à§ Ī
|
| 165 |
+
à§ ĭ
|
| 166 |
+
à§ į
|
| 167 |
+
à§ Ł
|
| 168 |
+
à© °
|
| 169 |
+
à© ±
|
| 170 |
+
à© ģ
|
| 171 |
+
à© Ĥ
|
| 172 |
+
à© ĩ
|
| 173 |
+
à© Ī
|
| 174 |
+
<\ s>
|
| 175 |
+
<p ad
|
| 176 |
+
âĪ Ĵ
|
| 177 |
+
<pad >
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9becaab2f4b54c9c5cc580f9691271807b30ff46e2e1db9e4f1b27bf8a63b36
|
| 3 |
+
size 21726893
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "</s>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,598 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "<\\s>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "<pad>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "<UNK>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 329,
|
| 44 |
+
"content": "</s>",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 330,
|
| 53 |
+
"content": "<unk>",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"special": true
|
| 59 |
+
}
|
| 60 |
+
],
|
| 61 |
+
"normalizer": null,
|
| 62 |
+
"pre_tokenizer": {
|
| 63 |
+
"type": "ByteLevel",
|
| 64 |
+
"add_prefix_space": false,
|
| 65 |
+
"trim_offsets": true,
|
| 66 |
+
"use_regex": false
|
| 67 |
+
},
|
| 68 |
+
"post_processor": {
|
| 69 |
+
"type": "ByteLevel",
|
| 70 |
+
"add_prefix_space": true,
|
| 71 |
+
"trim_offsets": true,
|
| 72 |
+
"use_regex": true
|
| 73 |
+
},
|
| 74 |
+
"decoder": {
|
| 75 |
+
"type": "ByteLevel",
|
| 76 |
+
"add_prefix_space": true,
|
| 77 |
+
"trim_offsets": true,
|
| 78 |
+
"use_regex": true
|
| 79 |
+
},
|
| 80 |
+
"model": {
|
| 81 |
+
"type": "BPE",
|
| 82 |
+
"dropout": null,
|
| 83 |
+
"unk_token": "<UNK>",
|
| 84 |
+
"continuing_subword_prefix": null,
|
| 85 |
+
"end_of_word_suffix": null,
|
| 86 |
+
"fuse_unk": false,
|
| 87 |
+
"byte_fallback": false,
|
| 88 |
+
"vocab": {
|
| 89 |
+
"<s>": 0,
|
| 90 |
+
"<\\s>": 1,
|
| 91 |
+
"<pad>": 2,
|
| 92 |
+
"<UNK>": 3,
|
| 93 |
+
"!": 4,
|
| 94 |
+
"%": 5,
|
| 95 |
+
"&": 6,
|
| 96 |
+
"(": 7,
|
| 97 |
+
")": 8,
|
| 98 |
+
"*": 9,
|
| 99 |
+
"+": 10,
|
| 100 |
+
",": 11,
|
| 101 |
+
"-": 12,
|
| 102 |
+
".": 13,
|
| 103 |
+
"/": 14,
|
| 104 |
+
"0": 15,
|
| 105 |
+
"1": 16,
|
| 106 |
+
"2": 17,
|
| 107 |
+
"3": 18,
|
| 108 |
+
"4": 19,
|
| 109 |
+
"5": 20,
|
| 110 |
+
"6": 21,
|
| 111 |
+
"7": 22,
|
| 112 |
+
"8": 23,
|
| 113 |
+
"9": 24,
|
| 114 |
+
":": 25,
|
| 115 |
+
";": 26,
|
| 116 |
+
"<": 27,
|
| 117 |
+
"=": 28,
|
| 118 |
+
">": 29,
|
| 119 |
+
"?": 30,
|
| 120 |
+
"A": 31,
|
| 121 |
+
"B": 32,
|
| 122 |
+
"C": 33,
|
| 123 |
+
"D": 34,
|
| 124 |
+
"E": 35,
|
| 125 |
+
"F": 36,
|
| 126 |
+
"G": 37,
|
| 127 |
+
"H": 38,
|
| 128 |
+
"I": 39,
|
| 129 |
+
"J": 40,
|
| 130 |
+
"K": 41,
|
| 131 |
+
"L": 42,
|
| 132 |
+
"M": 43,
|
| 133 |
+
"N": 44,
|
| 134 |
+
"O": 45,
|
| 135 |
+
"P": 46,
|
| 136 |
+
"Q": 47,
|
| 137 |
+
"R": 48,
|
| 138 |
+
"S": 49,
|
| 139 |
+
"T": 50,
|
| 140 |
+
"U": 51,
|
| 141 |
+
"V": 52,
|
| 142 |
+
"W": 53,
|
| 143 |
+
"X": 54,
|
| 144 |
+
"Y": 55,
|
| 145 |
+
"Z": 56,
|
| 146 |
+
"[": 57,
|
| 147 |
+
"\\": 58,
|
| 148 |
+
"]": 59,
|
| 149 |
+
"_": 60,
|
| 150 |
+
"`": 61,
|
| 151 |
+
"a": 62,
|
| 152 |
+
"b": 63,
|
| 153 |
+
"c": 64,
|
| 154 |
+
"d": 65,
|
| 155 |
+
"e": 66,
|
| 156 |
+
"f": 67,
|
| 157 |
+
"g": 68,
|
| 158 |
+
"h": 69,
|
| 159 |
+
"i": 70,
|
| 160 |
+
"j": 71,
|
| 161 |
+
"k": 72,
|
| 162 |
+
"l": 73,
|
| 163 |
+
"m": 74,
|
| 164 |
+
"n": 75,
|
| 165 |
+
"o": 76,
|
| 166 |
+
"p": 77,
|
| 167 |
+
"q": 78,
|
| 168 |
+
"r": 79,
|
| 169 |
+
"s": 80,
|
| 170 |
+
"t": 81,
|
| 171 |
+
"u": 82,
|
| 172 |
+
"v": 83,
|
| 173 |
+
"w": 84,
|
| 174 |
+
"x": 85,
|
| 175 |
+
"y": 86,
|
| 176 |
+
"z": 87,
|
| 177 |
+
"|": 88,
|
| 178 |
+
"~": 89,
|
| 179 |
+
"¡": 90,
|
| 180 |
+
"¢": 91,
|
| 181 |
+
"£": 92,
|
| 182 |
+
"¤": 93,
|
| 183 |
+
"¥": 94,
|
| 184 |
+
"¦": 95,
|
| 185 |
+
"§": 96,
|
| 186 |
+
"¨": 97,
|
| 187 |
+
"©": 98,
|
| 188 |
+
"ª": 99,
|
| 189 |
+
"«": 100,
|
| 190 |
+
"¬": 101,
|
| 191 |
+
"®": 102,
|
| 192 |
+
"¯": 103,
|
| 193 |
+
"°": 104,
|
| 194 |
+
"±": 105,
|
| 195 |
+
"²": 106,
|
| 196 |
+
"³": 107,
|
| 197 |
+
"µ": 108,
|
| 198 |
+
"¶": 109,
|
| 199 |
+
"·": 110,
|
| 200 |
+
"¸": 111,
|
| 201 |
+
"¹": 112,
|
| 202 |
+
"¼": 113,
|
| 203 |
+
"½": 114,
|
| 204 |
+
"¾": 115,
|
| 205 |
+
"¿": 116,
|
| 206 |
+
"Â": 117,
|
| 207 |
+
"Ã": 118,
|
| 208 |
+
"Ë": 119,
|
| 209 |
+
"à": 120,
|
| 210 |
+
"â": 121,
|
| 211 |
+
"Ġ": 122,
|
| 212 |
+
"Ģ": 123,
|
| 213 |
+
"ģ": 124,
|
| 214 |
+
"Ĥ": 125,
|
| 215 |
+
"ĥ": 126,
|
| 216 |
+
"Ħ": 127,
|
| 217 |
+
"ħ": 128,
|
| 218 |
+
"Ĩ": 129,
|
| 219 |
+
"ĩ": 130,
|
| 220 |
+
"Ī": 131,
|
| 221 |
+
"ī": 132,
|
| 222 |
+
"Ĭ": 133,
|
| 223 |
+
"ĭ": 134,
|
| 224 |
+
"Į": 135,
|
| 225 |
+
"į": 136,
|
| 226 |
+
"ı": 137,
|
| 227 |
+
"IJ": 138,
|
| 228 |
+
"ij": 139,
|
| 229 |
+
"Ĵ": 140,
|
| 230 |
+
"ĵ": 141,
|
| 231 |
+
"Ķ": 142,
|
| 232 |
+
"ķ": 143,
|
| 233 |
+
"ĸ": 144,
|
| 234 |
+
"Ĺ": 145,
|
| 235 |
+
"ĺ": 146,
|
| 236 |
+
"Ļ": 147,
|
| 237 |
+
"ļ": 148,
|
| 238 |
+
"Ľ": 149,
|
| 239 |
+
"ľ": 150,
|
| 240 |
+
"Ŀ": 151,
|
| 241 |
+
"ŀ": 152,
|
| 242 |
+
"Ł": 153,
|
| 243 |
+
"ł": 154,
|
| 244 |
+
"Ń": 155,
|
| 245 |
+
"à¤": 156,
|
| 246 |
+
"à¥": 157,
|
| 247 |
+
"à¦": 158,
|
| 248 |
+
"à¨": 159,
|
| 249 |
+
"âĢ": 160,
|
| 250 |
+
"à§": 161,
|
| 251 |
+
"à©": 162,
|
| 252 |
+
"s>": 163,
|
| 253 |
+
"<\\": 164,
|
| 254 |
+
"<p": 165,
|
| 255 |
+
"ad": 166,
|
| 256 |
+
"°": 167,
|
| 257 |
+
"²": 168,
|
| 258 |
+
"á": 169,
|
| 259 |
+
"è": 170,
|
| 260 |
+
"é": 171,
|
| 261 |
+
"÷": 172,
|
| 262 |
+
"ÃĹ": 173,
|
| 263 |
+
"Ëļ": 174,
|
| 264 |
+
"âĪ": 175,
|
| 265 |
+
"ड": 176,
|
| 266 |
+
"ढ": 177,
|
| 267 |
+
"ण": 178,
|
| 268 |
+
"त": 179,
|
| 269 |
+
"थ": 180,
|
| 270 |
+
"द": 181,
|
| 271 |
+
"ध": 182,
|
| 272 |
+
"न": 183,
|
| 273 |
+
"प": 184,
|
| 274 |
+
"फ": 185,
|
| 275 |
+
"ब": 186,
|
| 276 |
+
"म": 187,
|
| 277 |
+
"य": 188,
|
| 278 |
+
"र": 189,
|
| 279 |
+
"ल": 190,
|
| 280 |
+
"ळ": 191,
|
| 281 |
+
"व": 192,
|
| 282 |
+
"श": 193,
|
| 283 |
+
"ष": 194,
|
| 284 |
+
"स": 195,
|
| 285 |
+
"ह": 196,
|
| 286 |
+
"़": 197,
|
| 287 |
+
"ऽ": 198,
|
| 288 |
+
"ा": 199,
|
| 289 |
+
"ि": 200,
|
| 290 |
+
"à¤ģ": 201,
|
| 291 |
+
"à¤Ĥ": 202,
|
| 292 |
+
"à¤ĥ": 203,
|
| 293 |
+
"à¤ħ": 204,
|
| 294 |
+
"à¤Ĩ": 205,
|
| 295 |
+
"à¤ĩ": 206,
|
| 296 |
+
"à¤Ī": 207,
|
| 297 |
+
"à¤ī": 208,
|
| 298 |
+
"à¤Ĭ": 209,
|
| 299 |
+
"à¤ĭ": 210,
|
| 300 |
+
"à¤į": 211,
|
| 301 |
+
"à¤ı": 212,
|
| 302 |
+
"à¤IJ": 213,
|
| 303 |
+
"à¤ij": 214,
|
| 304 |
+
"à¤ĵ": 215,
|
| 305 |
+
"à¤Ķ": 216,
|
| 306 |
+
"à¤ķ": 217,
|
| 307 |
+
"à¤ĸ": 218,
|
| 308 |
+
"à¤Ĺ": 219,
|
| 309 |
+
"à¤ĺ": 220,
|
| 310 |
+
"à¤Ļ": 221,
|
| 311 |
+
"à¤ļ": 222,
|
| 312 |
+
"à¤Ľ": 223,
|
| 313 |
+
"à¤ľ": 224,
|
| 314 |
+
"à¤Ŀ": 225,
|
| 315 |
+
"à¤ŀ": 226,
|
| 316 |
+
"à¤Ł": 227,
|
| 317 |
+
"à¤ł": 228,
|
| 318 |
+
"à¤Ń": 229,
|
| 319 |
+
"।": 230,
|
| 320 |
+
"॥": 231,
|
| 321 |
+
"०": 232,
|
| 322 |
+
"१": 233,
|
| 323 |
+
"२": 234,
|
| 324 |
+
"३": 235,
|
| 325 |
+
"४": 236,
|
| 326 |
+
"५": 237,
|
| 327 |
+
"६": 238,
|
| 328 |
+
"८": 239,
|
| 329 |
+
"९": 240,
|
| 330 |
+
"à¥Ģ": 241,
|
| 331 |
+
"à¥ģ": 242,
|
| 332 |
+
"à¥Ĥ": 243,
|
| 333 |
+
"à¥ĥ": 244,
|
| 334 |
+
"à¥Ħ": 245,
|
| 335 |
+
"à¥ħ": 246,
|
| 336 |
+
"à¥ĩ": 247,
|
| 337 |
+
"à¥Ī": 248,
|
| 338 |
+
"à¥ī": 249,
|
| 339 |
+
"à¥Ĭ": 250,
|
| 340 |
+
"à¥ĭ": 251,
|
| 341 |
+
"à¥Į": 252,
|
| 342 |
+
"à¥į": 253,
|
| 343 |
+
"à¥IJ": 254,
|
| 344 |
+
"à¥ĺ": 255,
|
| 345 |
+
"à¥Ļ": 256,
|
| 346 |
+
"à¥ļ": 257,
|
| 347 |
+
"à¥Ľ": 258,
|
| 348 |
+
"à¥ľ": 259,
|
| 349 |
+
"à¥Ŀ": 260,
|
| 350 |
+
"à¥ŀ": 261,
|
| 351 |
+
"à¥Ł": 262,
|
| 352 |
+
"à¥ł": 263,
|
| 353 |
+
"à¥Ń": 264,
|
| 354 |
+
"ত": 265,
|
| 355 |
+
"থ": 266,
|
| 356 |
+
"ন": 267,
|
| 357 |
+
"প": 268,
|
| 358 |
+
"ব": 269,
|
| 359 |
+
"ম": 270,
|
| 360 |
+
"য": 271,
|
| 361 |
+
"ল": 272,
|
| 362 |
+
"স": 273,
|
| 363 |
+
"হ": 274,
|
| 364 |
+
"়": 275,
|
| 365 |
+
"া": 276,
|
| 366 |
+
"ি": 277,
|
| 367 |
+
"à¦Ĩ": 278,
|
| 368 |
+
"à¦ĩ": 279,
|
| 369 |
+
"à¦ı": 280,
|
| 370 |
+
"à¦ķ": 281,
|
| 371 |
+
"à¦Ĺ": 282,
|
| 372 |
+
"à¦ļ": 283,
|
| 373 |
+
"à¦Ľ": 284,
|
| 374 |
+
"à¦ľ": 285,
|
| 375 |
+
"à¦ł": 286,
|
| 376 |
+
"ਤ": 287,
|
| 377 |
+
"ਦ": 288,
|
| 378 |
+
"ਨ": 289,
|
| 379 |
+
"ਪ": 290,
|
| 380 |
+
"ਬ": 291,
|
| 381 |
+
"ਮ": 292,
|
| 382 |
+
"ਲ": 293,
|
| 383 |
+
"ਵ": 294,
|
| 384 |
+
"ਸ਼": 295,
|
| 385 |
+
"ਸ": 296,
|
| 386 |
+
"ਹ": 297,
|
| 387 |
+
"਼": 298,
|
| 388 |
+
"ਾ": 299,
|
| 389 |
+
"ਿ": 300,
|
| 390 |
+
"à¨ħ": 301,
|
| 391 |
+
"à¨Ĩ": 302,
|
| 392 |
+
"à¨ī": 303,
|
| 393 |
+
"à¨ķ": 304,
|
| 394 |
+
"à¨ĸ": 305,
|
| 395 |
+
"à¨ļ": 306,
|
| 396 |
+
"â̦": 307,
|
| 397 |
+
"âĢĮ": 308,
|
| 398 |
+
"âĢį": 309,
|
| 399 |
+
"âĢĵ": 310,
|
| 400 |
+
"âĢĺ": 311,
|
| 401 |
+
"âĢĻ": 312,
|
| 402 |
+
"âĢľ": 313,
|
| 403 |
+
"âĢĿ": 314,
|
| 404 |
+
"à§°": 315,
|
| 405 |
+
"à§±": 316,
|
| 406 |
+
"à§Ī": 317,
|
| 407 |
+
"à§ĭ": 318,
|
| 408 |
+
"à§į": 319,
|
| 409 |
+
"à§Ł": 320,
|
| 410 |
+
"à©°": 321,
|
| 411 |
+
"ੱ": 322,
|
| 412 |
+
"à©ģ": 323,
|
| 413 |
+
"à©Ĥ": 324,
|
| 414 |
+
"à©ĩ": 325,
|
| 415 |
+
"à©Ī": 326,
|
| 416 |
+
"<pad": 327,
|
| 417 |
+
"âĪĴ": 328
|
| 418 |
+
},
|
| 419 |
+
"merges": [
|
| 420 |
+
"à ¤",
|
| 421 |
+
"à ¥",
|
| 422 |
+
"à ¦",
|
| 423 |
+
"à ¨",
|
| 424 |
+
"â Ģ",
|
| 425 |
+
"à §",
|
| 426 |
+
"à ©",
|
| 427 |
+
"s >",
|
| 428 |
+
"< \\",
|
| 429 |
+
"< p",
|
| 430 |
+
"< s>",
|
| 431 |
+
"a d",
|
| 432 |
+
"Â °",
|
| 433 |
+
"Â ²",
|
| 434 |
+
"Ã ¡",
|
| 435 |
+
"Ã ¨",
|
| 436 |
+
"Ã ©",
|
| 437 |
+
"Ã ·",
|
| 438 |
+
"Ã Ĺ",
|
| 439 |
+
"Ë ļ",
|
| 440 |
+
"â Ī",
|
| 441 |
+
"ठ¡",
|
| 442 |
+
"ठ¢",
|
| 443 |
+
"ठ£",
|
| 444 |
+
"ठ¤",
|
| 445 |
+
"ठ¥",
|
| 446 |
+
"ठ¦",
|
| 447 |
+
"ठ§",
|
| 448 |
+
"ठ¨",
|
| 449 |
+
"ठª",
|
| 450 |
+
"ठ«",
|
| 451 |
+
"ठ¬",
|
| 452 |
+
"ठ®",
|
| 453 |
+
"ठ¯",
|
| 454 |
+
"ठ°",
|
| 455 |
+
"ठ²",
|
| 456 |
+
"ठ³",
|
| 457 |
+
"ठµ",
|
| 458 |
+
"ठ¶",
|
| 459 |
+
"ठ·",
|
| 460 |
+
"ठ¸",
|
| 461 |
+
"ठ¹",
|
| 462 |
+
"ठ¼",
|
| 463 |
+
"ठ½",
|
| 464 |
+
"ठ¾",
|
| 465 |
+
"ठ¿",
|
| 466 |
+
"ठģ",
|
| 467 |
+
"ठĤ",
|
| 468 |
+
"ठĥ",
|
| 469 |
+
"ठħ",
|
| 470 |
+
"ठĨ",
|
| 471 |
+
"ठĩ",
|
| 472 |
+
"ठĪ",
|
| 473 |
+
"ठī",
|
| 474 |
+
"ठĬ",
|
| 475 |
+
"ठĭ",
|
| 476 |
+
"ठį",
|
| 477 |
+
"ठı",
|
| 478 |
+
"ठIJ",
|
| 479 |
+
"ठij",
|
| 480 |
+
"ठĵ",
|
| 481 |
+
"ठĶ",
|
| 482 |
+
"ठķ",
|
| 483 |
+
"ठĸ",
|
| 484 |
+
"ठĹ",
|
| 485 |
+
"ठĺ",
|
| 486 |
+
"ठĻ",
|
| 487 |
+
"ठļ",
|
| 488 |
+
"ठĽ",
|
| 489 |
+
"ठľ",
|
| 490 |
+
"ठĿ",
|
| 491 |
+
"ठŀ",
|
| 492 |
+
"ठŁ",
|
| 493 |
+
"ठł",
|
| 494 |
+
"ठŃ",
|
| 495 |
+
"ॠ¤",
|
| 496 |
+
"ॠ¥",
|
| 497 |
+
"ॠ¦",
|
| 498 |
+
"ॠ§",
|
| 499 |
+
"ॠ¨",
|
| 500 |
+
"ॠ©",
|
| 501 |
+
"ॠª",
|
| 502 |
+
"ॠ«",
|
| 503 |
+
"ॠ¬",
|
| 504 |
+
"ॠ®",
|
| 505 |
+
"ॠ¯",
|
| 506 |
+
"ॠĢ",
|
| 507 |
+
"ॠģ",
|
| 508 |
+
"ॠĤ",
|
| 509 |
+
"ॠĥ",
|
| 510 |
+
"ॠĦ",
|
| 511 |
+
"ॠħ",
|
| 512 |
+
"ॠĩ",
|
| 513 |
+
"ॠĪ",
|
| 514 |
+
"ॠī",
|
| 515 |
+
"ॠĬ",
|
| 516 |
+
"ॠĭ",
|
| 517 |
+
"ॠĮ",
|
| 518 |
+
"ॠį",
|
| 519 |
+
"ॠIJ",
|
| 520 |
+
"ॠĺ",
|
| 521 |
+
"ॠĻ",
|
| 522 |
+
"ॠļ",
|
| 523 |
+
"ॠĽ",
|
| 524 |
+
"ॠľ",
|
| 525 |
+
"ॠĿ",
|
| 526 |
+
"ॠŀ",
|
| 527 |
+
"ॠŁ",
|
| 528 |
+
"ॠł",
|
| 529 |
+
"ॠŃ",
|
| 530 |
+
"ঠ¤",
|
| 531 |
+
"ঠ¥",
|
| 532 |
+
"ঠ¨",
|
| 533 |
+
"ঠª",
|
| 534 |
+
"ঠ¬",
|
| 535 |
+
"ঠ®",
|
| 536 |
+
"ঠ¯",
|
| 537 |
+
"ঠ²",
|
| 538 |
+
"ঠ¸",
|
| 539 |
+
"ঠ¹",
|
| 540 |
+
"ঠ¼",
|
| 541 |
+
"ঠ¾",
|
| 542 |
+
"ঠ¿",
|
| 543 |
+
"ঠĨ",
|
| 544 |
+
"ঠĩ",
|
| 545 |
+
"ঠı",
|
| 546 |
+
"ঠķ",
|
| 547 |
+
"ঠĹ",
|
| 548 |
+
"ঠļ",
|
| 549 |
+
"ঠĽ",
|
| 550 |
+
"ঠľ",
|
| 551 |
+
"ঠł",
|
| 552 |
+
"ਠ¤",
|
| 553 |
+
"ਠ¦",
|
| 554 |
+
"ਠ¨",
|
| 555 |
+
"ਠª",
|
| 556 |
+
"ਠ¬",
|
| 557 |
+
"ਠ®",
|
| 558 |
+
"ਠ²",
|
| 559 |
+
"ਠµ",
|
| 560 |
+
"ਠ¶",
|
| 561 |
+
"ਠ¸",
|
| 562 |
+
"ਠ¹",
|
| 563 |
+
"ਠ¼",
|
| 564 |
+
"ਠ¾",
|
| 565 |
+
"ਠ¿",
|
| 566 |
+
"ਠħ",
|
| 567 |
+
"ਠĨ",
|
| 568 |
+
"ਠī",
|
| 569 |
+
"ਠķ",
|
| 570 |
+
"ਠĸ",
|
| 571 |
+
"ਠļ",
|
| 572 |
+
"âĢ ¦",
|
| 573 |
+
"âĢ Į",
|
| 574 |
+
"âĢ į",
|
| 575 |
+
"âĢ ĵ",
|
| 576 |
+
"âĢ ĺ",
|
| 577 |
+
"âĢ Ļ",
|
| 578 |
+
"âĢ ľ",
|
| 579 |
+
"âĢ Ŀ",
|
| 580 |
+
"à§ °",
|
| 581 |
+
"à§ ±",
|
| 582 |
+
"à§ Ī",
|
| 583 |
+
"à§ ĭ",
|
| 584 |
+
"à§ į",
|
| 585 |
+
"à§ Ł",
|
| 586 |
+
"à© °",
|
| 587 |
+
"à© ±",
|
| 588 |
+
"à© ģ",
|
| 589 |
+
"à© Ĥ",
|
| 590 |
+
"à© ĩ",
|
| 591 |
+
"à© Ī",
|
| 592 |
+
"<\\ s>",
|
| 593 |
+
"<p ad",
|
| 594 |
+
"âĪ Ĵ",
|
| 595 |
+
"<pad >"
|
| 596 |
+
]
|
| 597 |
+
}
|
| 598 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d0a9e2942562cddfd25817cf85402c593ebcfc000a1637064b98ec239177eb9
|
| 3 |
+
size 3887
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<s>":0,"<\\s>":1,"<pad>":2,"<UNK>":3,"!":4,"%":5,"&":6,"(":7,")":8,"*":9,"+":10,",":11,"-":12,".":13,"/":14,"0":15,"1":16,"2":17,"3":18,"4":19,"5":20,"6":21,"7":22,"8":23,"9":24,":":25,";":26,"<":27,"=":28,">":29,"?":30,"A":31,"B":32,"C":33,"D":34,"E":35,"F":36,"G":37,"H":38,"I":39,"J":40,"K":41,"L":42,"M":43,"N":44,"O":45,"P":46,"Q":47,"R":48,"S":49,"T":50,"U":51,"V":52,"W":53,"X":54,"Y":55,"Z":56,"[":57,"\\":58,"]":59,"_":60,"`":61,"a":62,"b":63,"c":64,"d":65,"e":66,"f":67,"g":68,"h":69,"i":70,"j":71,"k":72,"l":73,"m":74,"n":75,"o":76,"p":77,"q":78,"r":79,"s":80,"t":81,"u":82,"v":83,"w":84,"x":85,"y":86,"z":87,"|":88,"~":89,"¡":90,"¢":91,"£":92,"¤":93,"¥":94,"¦":95,"§":96,"¨":97,"©":98,"ª":99,"«":100,"¬":101,"®":102,"¯":103,"°":104,"±":105,"²":106,"³":107,"µ":108,"¶":109,"·":110,"¸":111,"¹":112,"¼":113,"½":114,"¾":115,"¿":116,"Â":117,"Ã":118,"Ë":119,"à":120,"â":121,"Ġ":122,"Ģ":123,"ģ":124,"Ĥ":125,"ĥ":126,"Ħ":127,"ħ":128,"Ĩ":129,"ĩ":130,"Ī":131,"ī":132,"Ĭ":133,"ĭ":134,"Į":135,"į":136,"ı":137,"IJ":138,"ij":139,"Ĵ":140,"ĵ":141,"Ķ":142,"ķ":143,"ĸ":144,"Ĺ":145,"ĺ":146,"Ļ":147,"ļ":148,"Ľ":149,"ľ":150,"Ŀ":151,"ŀ":152,"Ł":153,"ł":154,"Ń":155,"à¤":156,"à¥":157,"à¦":158,"à¨":159,"âĢ":160,"à§":161,"à©":162,"s>":163,"<\\":164,"<p":165,"ad":166,"°":167,"²":168,"á":169,"è":170,"é":171,"÷":172,"ÃĹ":173,"Ëļ":174,"âĪ":175,"ड":176,"ढ":177,"ण":178,"त":179,"थ":180,"द":181,"ध":182,"न":183,"प":184,"फ":185,"ब":186,"म":187,"य":188,"र":189,"ल":190,"ळ":191,"व":192,"श":193,"ष":194,"स":195,"ह":196,"़":197,"ऽ":198,"ा":199,"ि":200,"à¤ģ":201,"à¤Ĥ":202,"à¤ĥ":203,"à¤ħ":204,"à¤Ĩ":205,"à¤ĩ":206,"à¤Ī":207,"à¤ī":208,"à¤Ĭ":209,"à¤ĭ":210,"à¤į":211,"à¤ı":212,"à¤IJ":213,"à¤ij":214,"à¤ĵ":215,"à¤Ķ":216,"à¤ķ":217,"à¤ĸ":218,"à¤Ĺ":219,"à¤ĺ":220,"à¤Ļ":221,"à¤ļ":222,"à¤Ľ":223,"à¤ľ":224,"à¤Ŀ":225,"à¤ŀ":226,"à¤Ł":227,"à¤ł":228,"à¤Ń":229,"।":230,"॥":231,"०":232,"१":233,"२":234,"३":235,"४":236,"५":237,"६":238,"८":239,"९":240,"à¥Ģ":241,"à¥ģ":242,"à¥Ĥ":243,"à¥ĥ":244,"à¥Ħ":245,"à¥ħ":246,"à¥ĩ":247,"à¥Ī":248,"à¥ī":249,"à¥Ĭ":250,"à¥ĭ":251,"à¥Į":252,"à¥į":253,"à¥IJ":254,"à¥ĺ":255,"à¥Ļ":256,"à¥ļ":257,"à¥Ľ":258,"à¥ľ":259,"à¥Ŀ":260,"à¥ŀ":261,"à¥Ł":262,"à¥ł":263,"à¥Ń":264,"ত":265,"থ":266,"ন":267,"প":268,"ব":269,"ম":270,"য":271,"ল":272,"স":273,"হ":274,"়":275,"া":276,"ি":277,"à¦Ĩ":278,"à¦ĩ":279,"à¦ı":280,"à¦ķ":281,"à¦Ĺ":282,"à¦ļ":283,"à¦Ľ":284,"à¦ľ":285,"à¦ł":286,"ਤ":287,"ਦ":288,"ਨ":289,"ਪ":290,"ਬ":291,"ਮ":292,"ਲ":293,"ਵ":294,"ਸ਼":295,"ਸ":296,"ਹ":297,"਼":298,"ਾ":299,"ਿ":300,"à¨ħ":301,"à¨Ĩ":302,"à¨ī":303,"à¨ķ":304,"à¨ĸ":305,"à¨ļ":306,"â̦":307,"âĢĮ":308,"âĢį":309,"âĢĵ":310,"âĢĺ":311,"âĢĻ":312,"âĢľ":313,"âĢĿ":314,"à§°":315,"à§±":316,"à§Ī":317,"à§ĭ":318,"à§į":319,"à§Ł":320,"à©°":321,"ੱ":322,"à©ģ":323,"à©Ĥ":324,"à©ĩ":325,"à©Ī":326,"<pad":327,"âĪĴ":328}
|