macabdul9 commited on
Commit
08498e9
·
verified ·
1 Parent(s): 8b1a9bc

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. README.md +38 -0
  2. added_tokens.json +127 -0
  3. config.json +22 -0
  4. configuration_egpt.py +35 -0
  5. model.safetensors +3 -0
  6. modeling_egpt.py +153 -0
  7. tokenizer_config.json +1165 -0
README.md ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - egpt
5
+ - llama-architecture
6
+ - decoder-only
7
+ - untrained
8
+ license: mit
9
+ ---
10
+
11
+ # eGPT-3B-untrained
12
+
13
+ Randomly initialized eGPT decoder-only model (3.22B parameters). **Not trained.**
14
+
15
+ ## Architecture
16
+
17
+ | Field | Value |
18
+ |---|---|
19
+ | Parameters | 3.22B |
20
+ | Layers | 32 |
21
+ | Dim | 3072 |
22
+ | Heads (Q) | 24 |
23
+ | Heads (KV) | 8 |
24
+ | Head dim | 128 |
25
+ | FFN hidden | 8192 |
26
+ | Max seq len | 2048 |
27
+ | Vocab size | 256 |
28
+ | Tokenizer | `google/byt5-small` |
29
+
30
+ ## Loading
31
+
32
+ ```python
33
+ from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer
34
+
35
+ tok = AutoTokenizer.from_pretrained("LLMsHub/eGPT-3B-untrained", trust_remote_code=True)
36
+ cfg = AutoConfig.from_pretrained("LLMsHub/eGPT-3B-untrained", trust_remote_code=True)
37
+ model = AutoModelForCausalLM.from_pretrained("LLMsHub/eGPT-3B-untrained", trust_remote_code=True)
38
+ ```
added_tokens.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 259,
3
+ "<extra_id_100>": 359,
4
+ "<extra_id_101>": 360,
5
+ "<extra_id_102>": 361,
6
+ "<extra_id_103>": 362,
7
+ "<extra_id_104>": 363,
8
+ "<extra_id_105>": 364,
9
+ "<extra_id_106>": 365,
10
+ "<extra_id_107>": 366,
11
+ "<extra_id_108>": 367,
12
+ "<extra_id_109>": 368,
13
+ "<extra_id_10>": 269,
14
+ "<extra_id_110>": 369,
15
+ "<extra_id_111>": 370,
16
+ "<extra_id_112>": 371,
17
+ "<extra_id_113>": 372,
18
+ "<extra_id_114>": 373,
19
+ "<extra_id_115>": 374,
20
+ "<extra_id_116>": 375,
21
+ "<extra_id_117>": 376,
22
+ "<extra_id_118>": 377,
23
+ "<extra_id_119>": 378,
24
+ "<extra_id_11>": 270,
25
+ "<extra_id_120>": 379,
26
+ "<extra_id_121>": 380,
27
+ "<extra_id_122>": 381,
28
+ "<extra_id_123>": 382,
29
+ "<extra_id_124>": 383,
30
+ "<extra_id_12>": 271,
31
+ "<extra_id_13>": 272,
32
+ "<extra_id_14>": 273,
33
+ "<extra_id_15>": 274,
34
+ "<extra_id_16>": 275,
35
+ "<extra_id_17>": 276,
36
+ "<extra_id_18>": 277,
37
+ "<extra_id_19>": 278,
38
+ "<extra_id_1>": 260,
39
+ "<extra_id_20>": 279,
40
+ "<extra_id_21>": 280,
41
+ "<extra_id_22>": 281,
42
+ "<extra_id_23>": 282,
43
+ "<extra_id_24>": 283,
44
+ "<extra_id_25>": 284,
45
+ "<extra_id_26>": 285,
46
+ "<extra_id_27>": 286,
47
+ "<extra_id_28>": 287,
48
+ "<extra_id_29>": 288,
49
+ "<extra_id_2>": 261,
50
+ "<extra_id_30>": 289,
51
+ "<extra_id_31>": 290,
52
+ "<extra_id_32>": 291,
53
+ "<extra_id_33>": 292,
54
+ "<extra_id_34>": 293,
55
+ "<extra_id_35>": 294,
56
+ "<extra_id_36>": 295,
57
+ "<extra_id_37>": 296,
58
+ "<extra_id_38>": 297,
59
+ "<extra_id_39>": 298,
60
+ "<extra_id_3>": 262,
61
+ "<extra_id_40>": 299,
62
+ "<extra_id_41>": 300,
63
+ "<extra_id_42>": 301,
64
+ "<extra_id_43>": 302,
65
+ "<extra_id_44>": 303,
66
+ "<extra_id_45>": 304,
67
+ "<extra_id_46>": 305,
68
+ "<extra_id_47>": 306,
69
+ "<extra_id_48>": 307,
70
+ "<extra_id_49>": 308,
71
+ "<extra_id_4>": 263,
72
+ "<extra_id_50>": 309,
73
+ "<extra_id_51>": 310,
74
+ "<extra_id_52>": 311,
75
+ "<extra_id_53>": 312,
76
+ "<extra_id_54>": 313,
77
+ "<extra_id_55>": 314,
78
+ "<extra_id_56>": 315,
79
+ "<extra_id_57>": 316,
80
+ "<extra_id_58>": 317,
81
+ "<extra_id_59>": 318,
82
+ "<extra_id_5>": 264,
83
+ "<extra_id_60>": 319,
84
+ "<extra_id_61>": 320,
85
+ "<extra_id_62>": 321,
86
+ "<extra_id_63>": 322,
87
+ "<extra_id_64>": 323,
88
+ "<extra_id_65>": 324,
89
+ "<extra_id_66>": 325,
90
+ "<extra_id_67>": 326,
91
+ "<extra_id_68>": 327,
92
+ "<extra_id_69>": 328,
93
+ "<extra_id_6>": 265,
94
+ "<extra_id_70>": 329,
95
+ "<extra_id_71>": 330,
96
+ "<extra_id_72>": 331,
97
+ "<extra_id_73>": 332,
98
+ "<extra_id_74>": 333,
99
+ "<extra_id_75>": 334,
100
+ "<extra_id_76>": 335,
101
+ "<extra_id_77>": 336,
102
+ "<extra_id_78>": 337,
103
+ "<extra_id_79>": 338,
104
+ "<extra_id_7>": 266,
105
+ "<extra_id_80>": 339,
106
+ "<extra_id_81>": 340,
107
+ "<extra_id_82>": 341,
108
+ "<extra_id_83>": 342,
109
+ "<extra_id_84>": 343,
110
+ "<extra_id_85>": 344,
111
+ "<extra_id_86>": 345,
112
+ "<extra_id_87>": 346,
113
+ "<extra_id_88>": 347,
114
+ "<extra_id_89>": 348,
115
+ "<extra_id_8>": 267,
116
+ "<extra_id_90>": 349,
117
+ "<extra_id_91>": 350,
118
+ "<extra_id_92>": 351,
119
+ "<extra_id_93>": 352,
120
+ "<extra_id_94>": 353,
121
+ "<extra_id_95>": 354,
122
+ "<extra_id_96>": 355,
123
+ "<extra_id_97>": 356,
124
+ "<extra_id_98>": 357,
125
+ "<extra_id_99>": 358,
126
+ "<extra_id_9>": 268
127
+ }
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "egpt",
3
+ "architectures": [
4
+ "eGPTForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_egpt.eGPTConfig",
8
+ "AutoModelForCausalLM": "modeling_egpt.eGPTForCausalLM"
9
+ },
10
+ "vocab_size": 256,
11
+ "dim": 3072,
12
+ "n_layers": 32,
13
+ "n_heads": 24,
14
+ "n_kv_heads": 8,
15
+ "head_dim": null,
16
+ "ffn_multiplier": 4.0,
17
+ "multiple_of": 256,
18
+ "max_seq_len": 2048,
19
+ "norm_eps": 1e-05,
20
+ "rope_theta": 10000.0,
21
+ "weight_tying": false
22
+ }
configuration_egpt.py ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from transformers import PreTrainedConfig
2
+
3
+
4
+ class eGPTConfig(PreTrainedConfig):
5
+ model_type = "egpt"
6
+
7
+ def __init__(
8
+ self,
9
+ vocab_size: int = 256,
10
+ dim: int = 768,
11
+ n_layers: int = 12,
12
+ n_heads: int = 12,
13
+ n_kv_heads: int = 12,
14
+ head_dim: int = None,
15
+ ffn_multiplier: float = 4.0,
16
+ multiple_of: int = 256,
17
+ max_seq_len: int = 2048,
18
+ norm_eps: float = 1e-5,
19
+ rope_theta: float = 10000.0,
20
+ weight_tying: bool = False,
21
+ **kwargs,
22
+ ):
23
+ super().__init__(**kwargs)
24
+ self.vocab_size = vocab_size
25
+ self.dim = dim
26
+ self.n_layers = n_layers
27
+ self.n_heads = n_heads
28
+ self.n_kv_heads = n_kv_heads
29
+ self.head_dim = head_dim
30
+ self.ffn_multiplier = ffn_multiplier
31
+ self.multiple_of = multiple_of
32
+ self.max_seq_len = max_seq_len
33
+ self.norm_eps = norm_eps
34
+ self.rope_theta = rope_theta
35
+ self.weight_tying = weight_tying
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e66d6146bd1305c45eaa5a037a10d46187dc09ac2ee04731ce123eb94310b78
3
+ size 12892021360
modeling_egpt.py ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """eGPT: LLaMA-style decoder-only model — self-contained HuggingFace implementation.
2
+
3
+ Architecture: RMSNorm, RoPE, Grouped-Query Attention, SwiGLU FFN, no bias.
4
+ Weight keys match eGPT/model.py exactly for checkpoint compatibility.
5
+ """
6
+
7
+ import math
8
+ from typing import Optional, Tuple
9
+
10
+ import torch
11
+ import torch.nn as nn
12
+ import torch.nn.functional as F
13
+ from transformers import PreTrainedModel
14
+ from transformers.generation import GenerationMixin
15
+ from transformers.modeling_outputs import CausalLMOutputWithPast
16
+
17
+ try:
18
+ from .configuration_egpt import eGPTConfig
19
+ except ImportError:
20
+ from configuration_egpt import eGPTConfig
21
+
22
+
23
+ class RMSNorm(nn.Module):
24
+ def __init__(self, dim: int, eps: float = 1e-5):
25
+ super().__init__()
26
+ self.eps = eps
27
+ self.weight = nn.Parameter(torch.ones(dim))
28
+
29
+ def forward(self, x: torch.Tensor) -> torch.Tensor:
30
+ return x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + self.eps) * self.weight
31
+
32
+
33
+ def _precompute_freqs_cis(head_dim: int, max_seq_len: int, theta: float) -> torch.Tensor:
34
+ freqs = 1.0 / (theta ** (torch.arange(0, head_dim, 2).float() / head_dim))
35
+ t = torch.arange(max_seq_len, dtype=torch.float32)
36
+ freqs = torch.outer(t, freqs)
37
+ return torch.polar(torch.ones_like(freqs), freqs)
38
+
39
+
40
+ def _apply_rotary_emb(xq: torch.Tensor, xk: torch.Tensor, freqs_cis: torch.Tensor):
41
+ def rotate(x):
42
+ xc = torch.view_as_complex(x.float().reshape(*x.shape[:-1], -1, 2))
43
+ f = freqs_cis.view(1, x.shape[1], 1, freqs_cis.shape[-1])
44
+ return torch.view_as_real(xc * f).flatten(-2).type_as(x)
45
+ return rotate(xq), rotate(xk)
46
+
47
+
48
+ class Attention(nn.Module):
49
+ def __init__(self, cfg: eGPTConfig):
50
+ super().__init__()
51
+ self.n_heads = cfg.n_heads
52
+ self.n_kv_heads = cfg.n_kv_heads
53
+ self.head_dim = cfg.head_dim or (cfg.dim // cfg.n_heads)
54
+ self.n_rep = cfg.n_heads // cfg.n_kv_heads
55
+
56
+ self.wq = nn.Linear(cfg.dim, cfg.n_heads * self.head_dim, bias=False)
57
+ self.wk = nn.Linear(cfg.dim, cfg.n_kv_heads * self.head_dim, bias=False)
58
+ self.wv = nn.Linear(cfg.dim, cfg.n_kv_heads * self.head_dim, bias=False)
59
+ self.wo = nn.Linear(cfg.n_heads * self.head_dim, cfg.dim, bias=False)
60
+
61
+ def forward(self, x: torch.Tensor, freqs_cis: torch.Tensor) -> torch.Tensor:
62
+ B, T, _ = x.shape
63
+ xq = self.wq(x).view(B, T, self.n_heads, self.head_dim)
64
+ xk = self.wk(x).view(B, T, self.n_kv_heads, self.head_dim)
65
+ xv = self.wv(x).view(B, T, self.n_kv_heads, self.head_dim)
66
+ xq, xk = _apply_rotary_emb(xq, xk, freqs_cis[:T])
67
+ if self.n_rep > 1:
68
+ xk = xk.repeat_interleave(self.n_rep, dim=2)
69
+ xv = xv.repeat_interleave(self.n_rep, dim=2)
70
+ out = F.scaled_dot_product_attention(
71
+ xq.transpose(1, 2), xk.transpose(1, 2), xv.transpose(1, 2), is_causal=True
72
+ )
73
+ return self.wo(out.transpose(1, 2).contiguous().view(B, T, -1))
74
+
75
+
76
+ class FeedForward(nn.Module):
77
+ def __init__(self, cfg: eGPTConfig):
78
+ super().__init__()
79
+ hidden = int(cfg.dim * cfg.ffn_multiplier * 2 / 3)
80
+ hidden = cfg.multiple_of * math.ceil(hidden / cfg.multiple_of)
81
+ self.w1 = nn.Linear(cfg.dim, hidden, bias=False)
82
+ self.w2 = nn.Linear(hidden, cfg.dim, bias=False)
83
+ self.w3 = nn.Linear(cfg.dim, hidden, bias=False)
84
+
85
+ def forward(self, x: torch.Tensor) -> torch.Tensor:
86
+ return self.w2(F.silu(self.w1(x)) * self.w3(x))
87
+
88
+
89
+ class TransformerBlock(nn.Module):
90
+ def __init__(self, cfg: eGPTConfig):
91
+ super().__init__()
92
+ self.attn_norm = RMSNorm(cfg.dim, cfg.norm_eps)
93
+ self.attn = Attention(cfg)
94
+ self.ffn_norm = RMSNorm(cfg.dim, cfg.norm_eps)
95
+ self.ffn = FeedForward(cfg)
96
+
97
+ def forward(self, x: torch.Tensor, freqs_cis: torch.Tensor) -> torch.Tensor:
98
+ x = x + self.attn(self.attn_norm(x), freqs_cis)
99
+ x = x + self.ffn(self.ffn_norm(x))
100
+ return x
101
+
102
+
103
+ class eGPTForCausalLM(PreTrainedModel, GenerationMixin):
104
+ config_class = eGPTConfig
105
+
106
+ def __init__(self, config: eGPTConfig):
107
+ super().__init__(config)
108
+ head_dim = config.head_dim or (config.dim // config.n_heads)
109
+
110
+ self.embed = nn.Embedding(config.vocab_size, config.dim)
111
+ self.layers = nn.ModuleList([TransformerBlock(config) for _ in range(config.n_layers)])
112
+ self.norm = RMSNorm(config.dim, config.norm_eps)
113
+ self.head = nn.Linear(config.dim, config.vocab_size, bias=False)
114
+
115
+ if config.weight_tying:
116
+ self.head.weight = self.embed.weight
117
+
118
+ freqs_cis = _precompute_freqs_cis(head_dim, config.max_seq_len * 2, config.rope_theta)
119
+ self.register_buffer("freqs_cis", freqs_cis, persistent=False)
120
+
121
+ self.post_init()
122
+
123
+ def get_input_embeddings(self):
124
+ return self.embed
125
+
126
+ def set_input_embeddings(self, value):
127
+ self.embed = value
128
+
129
+ def get_output_embeddings(self):
130
+ return self.head
131
+
132
+ def forward(
133
+ self,
134
+ input_ids: torch.Tensor,
135
+ attention_mask: Optional[torch.Tensor] = None,
136
+ labels: Optional[torch.Tensor] = None,
137
+ **kwargs,
138
+ ) -> CausalLMOutputWithPast:
139
+ x = self.embed(input_ids)
140
+ for layer in self.layers:
141
+ x = layer(x, self.freqs_cis)
142
+ x = self.norm(x)
143
+ logits = self.head(x)
144
+
145
+ loss = None
146
+ if labels is not None:
147
+ loss = F.cross_entropy(
148
+ logits.view(-1, logits.size(-1)).float(),
149
+ labels.reshape(-1),
150
+ ignore_index=-100,
151
+ )
152
+
153
+ return CausalLMOutputWithPast(loss=loss, logits=logits)
tokenizer_config.json ADDED
@@ -0,0 +1,1165 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "259": {
28
+ "content": "<extra_id_0>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "260": {
36
+ "content": "<extra_id_1>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "261": {
44
+ "content": "<extra_id_2>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "262": {
52
+ "content": "<extra_id_3>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "263": {
60
+ "content": "<extra_id_4>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "264": {
68
+ "content": "<extra_id_5>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "265": {
76
+ "content": "<extra_id_6>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "266": {
84
+ "content": "<extra_id_7>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "267": {
92
+ "content": "<extra_id_8>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "268": {
100
+ "content": "<extra_id_9>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "269": {
108
+ "content": "<extra_id_10>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "270": {
116
+ "content": "<extra_id_11>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "271": {
124
+ "content": "<extra_id_12>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "272": {
132
+ "content": "<extra_id_13>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "273": {
140
+ "content": "<extra_id_14>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "274": {
148
+ "content": "<extra_id_15>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "275": {
156
+ "content": "<extra_id_16>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "276": {
164
+ "content": "<extra_id_17>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "277": {
172
+ "content": "<extra_id_18>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "278": {
180
+ "content": "<extra_id_19>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "279": {
188
+ "content": "<extra_id_20>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "280": {
196
+ "content": "<extra_id_21>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "281": {
204
+ "content": "<extra_id_22>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "282": {
212
+ "content": "<extra_id_23>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "283": {
220
+ "content": "<extra_id_24>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "284": {
228
+ "content": "<extra_id_25>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "285": {
236
+ "content": "<extra_id_26>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "286": {
244
+ "content": "<extra_id_27>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "287": {
252
+ "content": "<extra_id_28>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "288": {
260
+ "content": "<extra_id_29>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "289": {
268
+ "content": "<extra_id_30>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "290": {
276
+ "content": "<extra_id_31>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "291": {
284
+ "content": "<extra_id_32>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "292": {
292
+ "content": "<extra_id_33>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "293": {
300
+ "content": "<extra_id_34>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "294": {
308
+ "content": "<extra_id_35>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "295": {
316
+ "content": "<extra_id_36>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "296": {
324
+ "content": "<extra_id_37>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "297": {
332
+ "content": "<extra_id_38>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "298": {
340
+ "content": "<extra_id_39>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "299": {
348
+ "content": "<extra_id_40>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "300": {
356
+ "content": "<extra_id_41>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "301": {
364
+ "content": "<extra_id_42>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "302": {
372
+ "content": "<extra_id_43>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "303": {
380
+ "content": "<extra_id_44>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "304": {
388
+ "content": "<extra_id_45>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "305": {
396
+ "content": "<extra_id_46>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "306": {
404
+ "content": "<extra_id_47>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "307": {
412
+ "content": "<extra_id_48>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "308": {
420
+ "content": "<extra_id_49>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "309": {
428
+ "content": "<extra_id_50>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "310": {
436
+ "content": "<extra_id_51>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "311": {
444
+ "content": "<extra_id_52>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "312": {
452
+ "content": "<extra_id_53>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "313": {
460
+ "content": "<extra_id_54>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "314": {
468
+ "content": "<extra_id_55>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "315": {
476
+ "content": "<extra_id_56>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "316": {
484
+ "content": "<extra_id_57>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "317": {
492
+ "content": "<extra_id_58>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "318": {
500
+ "content": "<extra_id_59>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "319": {
508
+ "content": "<extra_id_60>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "320": {
516
+ "content": "<extra_id_61>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "321": {
524
+ "content": "<extra_id_62>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "322": {
532
+ "content": "<extra_id_63>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "323": {
540
+ "content": "<extra_id_64>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "324": {
548
+ "content": "<extra_id_65>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "325": {
556
+ "content": "<extra_id_66>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "326": {
564
+ "content": "<extra_id_67>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "327": {
572
+ "content": "<extra_id_68>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "328": {
580
+ "content": "<extra_id_69>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "329": {
588
+ "content": "<extra_id_70>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "330": {
596
+ "content": "<extra_id_71>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "331": {
604
+ "content": "<extra_id_72>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "332": {
612
+ "content": "<extra_id_73>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "333": {
620
+ "content": "<extra_id_74>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "334": {
628
+ "content": "<extra_id_75>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "335": {
636
+ "content": "<extra_id_76>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "336": {
644
+ "content": "<extra_id_77>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "337": {
652
+ "content": "<extra_id_78>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "338": {
660
+ "content": "<extra_id_79>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "339": {
668
+ "content": "<extra_id_80>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "340": {
676
+ "content": "<extra_id_81>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "341": {
684
+ "content": "<extra_id_82>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "342": {
692
+ "content": "<extra_id_83>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "343": {
700
+ "content": "<extra_id_84>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "344": {
708
+ "content": "<extra_id_85>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "345": {
716
+ "content": "<extra_id_86>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "346": {
724
+ "content": "<extra_id_87>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "347": {
732
+ "content": "<extra_id_88>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "348": {
740
+ "content": "<extra_id_89>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "349": {
748
+ "content": "<extra_id_90>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "350": {
756
+ "content": "<extra_id_91>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "351": {
764
+ "content": "<extra_id_92>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "352": {
772
+ "content": "<extra_id_93>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "353": {
780
+ "content": "<extra_id_94>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "354": {
788
+ "content": "<extra_id_95>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "355": {
796
+ "content": "<extra_id_96>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "356": {
804
+ "content": "<extra_id_97>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "357": {
812
+ "content": "<extra_id_98>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "358": {
820
+ "content": "<extra_id_99>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "359": {
828
+ "content": "<extra_id_100>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "360": {
836
+ "content": "<extra_id_101>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "361": {
844
+ "content": "<extra_id_102>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "362": {
852
+ "content": "<extra_id_103>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "363": {
860
+ "content": "<extra_id_104>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "364": {
868
+ "content": "<extra_id_105>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "365": {
876
+ "content": "<extra_id_106>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "366": {
884
+ "content": "<extra_id_107>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "367": {
892
+ "content": "<extra_id_108>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "368": {
900
+ "content": "<extra_id_109>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "369": {
908
+ "content": "<extra_id_110>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "370": {
916
+ "content": "<extra_id_111>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "371": {
924
+ "content": "<extra_id_112>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "372": {
932
+ "content": "<extra_id_113>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "373": {
940
+ "content": "<extra_id_114>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "374": {
948
+ "content": "<extra_id_115>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "375": {
956
+ "content": "<extra_id_116>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "376": {
964
+ "content": "<extra_id_117>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "377": {
972
+ "content": "<extra_id_118>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "378": {
980
+ "content": "<extra_id_119>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "379": {
988
+ "content": "<extra_id_120>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "380": {
996
+ "content": "<extra_id_121>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "381": {
1004
+ "content": "<extra_id_122>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "382": {
1012
+ "content": "<extra_id_123>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "383": {
1020
+ "content": "<extra_id_124>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ }
1027
+ },
1028
+ "additional_special_tokens": [
1029
+ "<extra_id_0>",
1030
+ "<extra_id_1>",
1031
+ "<extra_id_2>",
1032
+ "<extra_id_3>",
1033
+ "<extra_id_4>",
1034
+ "<extra_id_5>",
1035
+ "<extra_id_6>",
1036
+ "<extra_id_7>",
1037
+ "<extra_id_8>",
1038
+ "<extra_id_9>",
1039
+ "<extra_id_10>",
1040
+ "<extra_id_11>",
1041
+ "<extra_id_12>",
1042
+ "<extra_id_13>",
1043
+ "<extra_id_14>",
1044
+ "<extra_id_15>",
1045
+ "<extra_id_16>",
1046
+ "<extra_id_17>",
1047
+ "<extra_id_18>",
1048
+ "<extra_id_19>",
1049
+ "<extra_id_20>",
1050
+ "<extra_id_21>",
1051
+ "<extra_id_22>",
1052
+ "<extra_id_23>",
1053
+ "<extra_id_24>",
1054
+ "<extra_id_25>",
1055
+ "<extra_id_26>",
1056
+ "<extra_id_27>",
1057
+ "<extra_id_28>",
1058
+ "<extra_id_29>",
1059
+ "<extra_id_30>",
1060
+ "<extra_id_31>",
1061
+ "<extra_id_32>",
1062
+ "<extra_id_33>",
1063
+ "<extra_id_34>",
1064
+ "<extra_id_35>",
1065
+ "<extra_id_36>",
1066
+ "<extra_id_37>",
1067
+ "<extra_id_38>",
1068
+ "<extra_id_39>",
1069
+ "<extra_id_40>",
1070
+ "<extra_id_41>",
1071
+ "<extra_id_42>",
1072
+ "<extra_id_43>",
1073
+ "<extra_id_44>",
1074
+ "<extra_id_45>",
1075
+ "<extra_id_46>",
1076
+ "<extra_id_47>",
1077
+ "<extra_id_48>",
1078
+ "<extra_id_49>",
1079
+ "<extra_id_50>",
1080
+ "<extra_id_51>",
1081
+ "<extra_id_52>",
1082
+ "<extra_id_53>",
1083
+ "<extra_id_54>",
1084
+ "<extra_id_55>",
1085
+ "<extra_id_56>",
1086
+ "<extra_id_57>",
1087
+ "<extra_id_58>",
1088
+ "<extra_id_59>",
1089
+ "<extra_id_60>",
1090
+ "<extra_id_61>",
1091
+ "<extra_id_62>",
1092
+ "<extra_id_63>",
1093
+ "<extra_id_64>",
1094
+ "<extra_id_65>",
1095
+ "<extra_id_66>",
1096
+ "<extra_id_67>",
1097
+ "<extra_id_68>",
1098
+ "<extra_id_69>",
1099
+ "<extra_id_70>",
1100
+ "<extra_id_71>",
1101
+ "<extra_id_72>",
1102
+ "<extra_id_73>",
1103
+ "<extra_id_74>",
1104
+ "<extra_id_75>",
1105
+ "<extra_id_76>",
1106
+ "<extra_id_77>",
1107
+ "<extra_id_78>",
1108
+ "<extra_id_79>",
1109
+ "<extra_id_80>",
1110
+ "<extra_id_81>",
1111
+ "<extra_id_82>",
1112
+ "<extra_id_83>",
1113
+ "<extra_id_84>",
1114
+ "<extra_id_85>",
1115
+ "<extra_id_86>",
1116
+ "<extra_id_87>",
1117
+ "<extra_id_88>",
1118
+ "<extra_id_89>",
1119
+ "<extra_id_90>",
1120
+ "<extra_id_91>",
1121
+ "<extra_id_92>",
1122
+ "<extra_id_93>",
1123
+ "<extra_id_94>",
1124
+ "<extra_id_95>",
1125
+ "<extra_id_96>",
1126
+ "<extra_id_97>",
1127
+ "<extra_id_98>",
1128
+ "<extra_id_99>",
1129
+ "<extra_id_100>",
1130
+ "<extra_id_101>",
1131
+ "<extra_id_102>",
1132
+ "<extra_id_103>",
1133
+ "<extra_id_104>",
1134
+ "<extra_id_105>",
1135
+ "<extra_id_106>",
1136
+ "<extra_id_107>",
1137
+ "<extra_id_108>",
1138
+ "<extra_id_109>",
1139
+ "<extra_id_110>",
1140
+ "<extra_id_111>",
1141
+ "<extra_id_112>",
1142
+ "<extra_id_113>",
1143
+ "<extra_id_114>",
1144
+ "<extra_id_115>",
1145
+ "<extra_id_116>",
1146
+ "<extra_id_117>",
1147
+ "<extra_id_118>",
1148
+ "<extra_id_119>",
1149
+ "<extra_id_120>",
1150
+ "<extra_id_121>",
1151
+ "<extra_id_122>",
1152
+ "<extra_id_123>",
1153
+ "<extra_id_124>"
1154
+ ],
1155
+ "backend": "custom",
1156
+ "eos_token": "</s>",
1157
+ "extra_ids": 0,
1158
+ "extra_special_tokens": {},
1159
+ "is_local": false,
1160
+ "local_files_only": false,
1161
+ "model_max_length": 1000000000000000019884624838656,
1162
+ "pad_token": "<pad>",
1163
+ "tokenizer_class": "ByT5Tokenizer",
1164
+ "unk_token": "<unk>"
1165
+ }