Hugging Face's logo

KoichiYasuoka
/
Llama-3-Swallow-8B-char-upos

Token Classification
Transformers
PyTorch
Japanese
llama
japanese
pos
text-generation-inference
Inference Endpoints
Model card Files Community
KoichiYasuoka commited on
Commit
d7de51e
•
1 Parent(s): edee6d3

initial release

Browse files
Files changed (14) hide show
  1. README.md +29 -0
  2. config.json +162 -0
  3. pytorch_model-00001-of-00007.bin +3 -0
  4. pytorch_model-00002-of-00007.bin +3 -0
  5. pytorch_model-00003-of-00007.bin +3 -0
  6. pytorch_model-00004-of-00007.bin +3 -0
  7. pytorch_model-00005-of-00007.bin +3 -0
  8. pytorch_model-00006-of-00007.bin +3 -0
  9. pytorch_model-00007-of-00007.bin +3 -0
  10. pytorch_model.bin.index.json +299 -0
  11. special_tokens_map.json +51 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +2090 -0
  14. upos.py +76 -0
README.md ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - "ja"
4
+ tags:
5
+ - "japanese"
6
+ - "token-classification"
7
+ - "pos"
8
+ datasets:
9
+ - "universal_dependencies"
10
+ license: "llama3"
11
+ pipeline_tag: "token-classification"
12
+ widget:
13
+ - text: "国境の長いトンネルを抜けると雪国であった。"
14
+ ---
15
+
16
+ # Llama-3-Swallow-8B-char-upos
17
+
18
+ ## Model Description
19
+
20
+ This is a LLaMA model for POS-tagging, derived from [Llama-3-Swallow-8B-v0.1](https://huggingface.co/tokyotech-llm/Llama-3-Swallow-8B-v0.1). Every short-unit-word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech) and [FEATS](https://universaldependencies.org/u/feat/).
21
+
22
+ ## How to Use
23
+
24
+ ```py
25
+ from transformers import pipeline
26
+ nlp=pipeline("upos","KoichiYasuoka/Llama-3-Swallow-8B-char-upos",trust_remote_code=True,aggregation_strategy="simple")
27
+ print(nlp("国境の長いトンネルを抜けると雪国であった。"))
28
+ ```
29
+
config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForTokenClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoModelForTokenClassification": "upos.LlamaForTokenClassification"
9
+ },
10
+ "bos_token_id": 128000,
11
+ "custom_pipelines": {
12
+ "upos": {
13
+ "impl": "upos.BellmanFordTokenClassificationPipeline",
14
+ "pt": "AutoModelForTokenClassification"
15
+ }
16
+ },
17
+ "eos_token_id": 128001,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 4096,
20
+ "id2label": {
21
+ "0": "ADJ",
22
+ "1": "B-ADJ",
23
+ "2": "I-ADJ",
24
+ "3": "ADJ|Polarity=Neg",
25
+ "4": "B-ADJ|Polarity=Neg",
26
+ "5": "I-ADJ|Polarity=Neg",
27
+ "6": "ADP",
28
+ "7": "B-ADP",
29
+ "8": "I-ADP",
30
+ "9": "ADV",
31
+ "10": "B-ADV",
32
+ "11": "I-ADV",
33
+ "12": "AUX",
34
+ "13": "B-AUX",
35
+ "14": "I-AUX",
36
+ "15": "AUX|Polarity=Neg",
37
+ "16": "B-AUX|Polarity=Neg",
38
+ "17": "I-AUX|Polarity=Neg",
39
+ "18": "CCONJ",
40
+ "19": "B-CCONJ",
41
+ "20": "I-CCONJ",
42
+ "21": "DET",
43
+ "22": "B-DET",
44
+ "23": "I-DET",
45
+ "24": "INTJ",
46
+ "25": "B-INTJ",
47
+ "26": "I-INTJ",
48
+ "27": "NOUN",
49
+ "28": "B-NOUN",
50
+ "29": "I-NOUN",
51
+ "30": "NOUN|Polarity=Neg",
52
+ "31": "B-NOUN|Polarity=Neg",
53
+ "32": "I-NOUN|Polarity=Neg",
54
+ "33": "NUM",
55
+ "34": "B-NUM",
56
+ "35": "I-NUM",
57
+ "36": "PART",
58
+ "37": "B-PART",
59
+ "38": "I-PART",
60
+ "39": "PRON",
61
+ "40": "B-PRON",
62
+ "41": "I-PRON",
63
+ "42": "PROPN",
64
+ "43": "B-PROPN",
65
+ "44": "I-PROPN",
66
+ "45": "PUNCT",
67
+ "46": "B-PUNCT",
68
+ "47": "I-PUNCT",
69
+ "48": "SCONJ",
70
+ "49": "B-SCONJ",
71
+ "50": "I-SCONJ",
72
+ "51": "SYM",
73
+ "52": "B-SYM",
74
+ "53": "I-SYM",
75
+ "54": "VERB",
76
+ "55": "B-VERB",
77
+ "56": "I-VERB",
78
+ "57": "X",
79
+ "58": "B-X",
80
+ "59": "I-X"
81
+ },
82
+ "initializer_range": 0.02,
83
+ "intermediate_size": 14336,
84
+ "label2id": {
85
+ "ADJ": 0,
86
+ "ADJ|Polarity=Neg": 3,
87
+ "ADP": 6,
88
+ "ADV": 9,
89
+ "AUX": 12,
90
+ "AUX|Polarity=Neg": 15,
91
+ "B-ADJ": 1,
92
+ "B-ADJ|Polarity=Neg": 4,
93
+ "B-ADP": 7,
94
+ "B-ADV": 10,
95
+ "B-AUX": 13,
96
+ "B-AUX|Polarity=Neg": 16,
97
+ "B-CCONJ": 19,
98
+ "B-DET": 22,
99
+ "B-INTJ": 25,
100
+ "B-NOUN": 28,
101
+ "B-NOUN|Polarity=Neg": 31,
102
+ "B-NUM": 34,
103
+ "B-PART": 37,
104
+ "B-PRON": 40,
105
+ "B-PROPN": 43,
106
+ "B-PUNCT": 46,
107
+ "B-SCONJ": 49,
108
+ "B-SYM": 52,
109
+ "B-VERB": 55,
110
+ "B-X": 58,
111
+ "CCONJ": 18,
112
+ "DET": 21,
113
+ "I-ADJ": 2,
114
+ "I-ADJ|Polarity=Neg": 5,
115
+ "I-ADP": 8,
116
+ "I-ADV": 11,
117
+ "I-AUX": 14,
118
+ "I-AUX|Polarity=Neg": 17,
119
+ "I-CCONJ": 20,
120
+ "I-DET": 23,
121
+ "I-INTJ": 26,
122
+ "I-NOUN": 29,
123
+ "I-NOUN|Polarity=Neg": 32,
124
+ "I-NUM": 35,
125
+ "I-PART": 38,
126
+ "I-PRON": 41,
127
+ "I-PROPN": 44,
128
+ "I-PUNCT": 47,
129
+ "I-SCONJ": 50,
130
+ "I-SYM": 53,
131
+ "I-VERB": 56,
132
+ "I-X": 59,
133
+ "INTJ": 24,
134
+ "NOUN": 27,
135
+ "NOUN|Polarity=Neg": 30,
136
+ "NUM": 33,
137
+ "PART": 36,
138
+ "PRON": 39,
139
+ "PROPN": 42,
140
+ "PUNCT": 45,
141
+ "SCONJ": 48,
142
+ "SYM": 51,
143
+ "VERB": 54,
144
+ "X": 57
145
+ },
146
+ "max_position_embeddings": 8192,
147
+ "mlp_bias": false,
148
+ "model_type": "llama",
149
+ "num_attention_heads": 32,
150
+ "num_hidden_layers": 32,
151
+ "num_key_value_heads": 8,
152
+ "pretraining_tp": 1,
153
+ "rms_norm_eps": 1e-05,
154
+ "rope_scaling": null,
155
+ "rope_theta": 500000.0,
156
+ "tie_word_embeddings": false,
157
+ "torch_dtype": "float32",
158
+ "tokenizer_class": "LlamaTokenizerFast",
159
+ "transformers_version": "4.41.2",
160
+ "use_cache": true,
161
+ "vocab_size": 128259
162
+ }
pytorch_model-00001-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c1020becbd2967f7776b863723430ec6d821af391f86662e027cefe447bba6
3
+ size 4886522810
pytorch_model-00002-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c2d24bf362a0d7c776dc4d18c27b40a1efd28541cda74edf14337cee9e305a3
3
+ size 4832018324
pytorch_model-00003-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb5f92fb8782e507f6e2ae881e536aa67aaf69e3f7981eecb7280d587f4238a
3
+ size 4999825256
pytorch_model-00004-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96889f5352ed44150847ae0c664665510991ad2fcfec15a798828a6ddc2b9aeb
3
+ size 4999825316
pytorch_model-00005-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b993fe8ca469d962e58c3e5d2c0d98e8c658257da743cccf8cbb7ee486570650
3
+ size 4832018324
pytorch_model-00006-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a17fc52fd91941f772c7165f87c942fb74899c7bb28e07c2a5c8d4c51bb2cb18
3
+ size 4999825320
pytorch_model-00007-of-00007.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efd153934df07485b3201de6e71a8ebff835646721cf6ce5e9099fb039749ace
3
+ size 470797675
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 30020731120
4
+ },
5
+ "weight_map": {
6
+ "classifier.bias": "pytorch_model-00007-of-00007.bin",
7
+ "classifier.weight": "pytorch_model-00007-of-00007.bin",
8
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
9
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
11
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
12
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
13
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
14
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
15
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
16
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
26
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
27
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
28
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
29
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
30
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
31
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
32
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
33
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
34
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
35
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
36
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
37
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
38
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
39
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
40
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
41
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
42
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
43
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
44
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
45
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
46
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
47
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
48
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
49
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
50
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
51
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
52
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
53
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
54
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
55
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
56
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
57
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
58
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
59
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
60
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
61
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
62
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
63
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
64
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
65
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
66
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
67
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
68
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
69
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
70
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
71
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
72
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
73
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
74
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
75
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
76
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
77
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
78
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
79
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
80
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
81
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
82
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
83
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
84
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
85
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
86
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
87
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
88
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
89
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
90
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
91
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
92
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
93
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
94
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
95
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
96
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
97
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
98
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
99
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
100
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
101
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
102
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
103
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
104
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
105
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
106
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
107
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
108
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
109
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
110
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
111
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
112
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
113
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
114
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
115
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
116
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
117
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
118
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
119
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
120
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
121
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
122
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
123
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
124
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
125
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
126
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
127
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
128
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
129
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
130
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
131
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
132
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
133
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
134
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
135
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
136
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
137
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
138
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
139
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
140
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
141
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
142
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
143
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
144
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
145
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
146
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
147
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
148
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
149
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
150
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
151
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
152
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
153
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
154
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
155
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
156
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
157
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
158
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
159
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
160
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
161
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
162
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
163
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
164
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
165
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
166
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
167
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
168
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
169
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
170
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
171
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
172
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
173
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
174
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
175
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
176
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
177
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
178
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
179
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
180
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
181
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
182
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
183
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
184
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
185
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
186
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
187
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
188
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
189
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
190
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
191
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
192
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
193
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
194
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
195
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
196
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
197
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
198
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
199
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
200
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
201
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
202
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
203
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
204
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
205
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
206
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
207
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
208
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
209
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
210
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
211
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
212
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
213
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
214
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
215
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
216
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
217
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
218
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
219
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
220
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
221
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
222
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
223
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
224
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
225
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
226
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
227
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
228
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
229
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
230
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
231
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
232
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
233
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
234
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
235
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
236
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
237
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
238
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
239
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
240
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
241
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
242
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
243
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
244
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
245
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
246
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
247
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
248
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
249
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
250
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
251
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
252
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
253
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
254
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
255
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
256
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
257
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
258
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
259
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
260
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
261
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
262
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
263
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
264
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
265
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
266
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
267
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
268
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
269
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
270
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
271
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
272
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
273
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
274
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
275
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
276
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
277
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
278
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
279
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
280
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
281
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
282
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
283
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
284
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
285
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
286
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
287
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
288
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
289
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
290
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
291
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
292
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
293
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
294
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
295
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
296
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
297
+ "model.norm.weight": "pytorch_model-00007-of-00007.bin"
298
+ }
299
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "</s>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "<s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2090 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "128000": {
6
+ "content": "<|begin_of_text|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "128001": {
14
+ "content": "<|end_of_text|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "128002": {
22
+ "content": "<|reserved_special_token_0|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "128003": {
30
+ "content": "<|reserved_special_token_1|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "128004": {
38
+ "content": "<|reserved_special_token_2|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "128005": {
46
+ "content": "<|reserved_special_token_3|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "128006": {
54
+ "content": "<|start_header_id|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "128007": {
62
+ "content": "<|end_header_id|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "128008": {
70
+ "content": "<|reserved_special_token_4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "128009": {
78
+ "content": "<|eot_id|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "128010": {
86
+ "content": "<|reserved_special_token_5|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "128011": {
94
+ "content": "<|reserved_special_token_6|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "128012": {
102
+ "content": "<|reserved_special_token_7|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "128013": {
110
+ "content": "<|reserved_special_token_8|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "128014": {
118
+ "content": "<|reserved_special_token_9|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "128015": {
126
+ "content": "<|reserved_special_token_10|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "128016": {
134
+ "content": "<|reserved_special_token_11|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "128017": {
142
+ "content": "<|reserved_special_token_12|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "128018": {
150
+ "content": "<|reserved_special_token_13|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "128019": {
158
+ "content": "<|reserved_special_token_14|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "128020": {
166
+ "content": "<|reserved_special_token_15|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "128021": {
174
+ "content": "<|reserved_special_token_16|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "128022": {
182
+ "content": "<|reserved_special_token_17|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "128023": {
190
+ "content": "<|reserved_special_token_18|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "128024": {
198
+ "content": "<|reserved_special_token_19|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "128025": {
206
+ "content": "<|reserved_special_token_20|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "128026": {
214
+ "content": "<|reserved_special_token_21|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "128027": {
222
+ "content": "<|reserved_special_token_22|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "128028": {
230
+ "content": "<|reserved_special_token_23|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "128029": {
238
+ "content": "<|reserved_special_token_24|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "128030": {
246
+ "content": "<|reserved_special_token_25|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "128031": {
254
+ "content": "<|reserved_special_token_26|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "128032": {
262
+ "content": "<|reserved_special_token_27|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "128033": {
270
+ "content": "<|reserved_special_token_28|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "128034": {
278
+ "content": "<|reserved_special_token_29|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "128035": {
286
+ "content": "<|reserved_special_token_30|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "128036": {
294
+ "content": "<|reserved_special_token_31|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "128037": {
302
+ "content": "<|reserved_special_token_32|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "128038": {
310
+ "content": "<|reserved_special_token_33|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "128039": {
318
+ "content": "<|reserved_special_token_34|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "128040": {
326
+ "content": "<|reserved_special_token_35|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "128041": {
334
+ "content": "<|reserved_special_token_36|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "128042": {
342
+ "content": "<|reserved_special_token_37|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "128043": {
350
+ "content": "<|reserved_special_token_38|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "128044": {
358
+ "content": "<|reserved_special_token_39|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "128045": {
366
+ "content": "<|reserved_special_token_40|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "128046": {
374
+ "content": "<|reserved_special_token_41|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "128047": {
382
+ "content": "<|reserved_special_token_42|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "128048": {
390
+ "content": "<|reserved_special_token_43|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "128049": {
398
+ "content": "<|reserved_special_token_44|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "128050": {
406
+ "content": "<|reserved_special_token_45|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "128051": {
414
+ "content": "<|reserved_special_token_46|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "128052": {
422
+ "content": "<|reserved_special_token_47|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "128053": {
430
+ "content": "<|reserved_special_token_48|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "128054": {
438
+ "content": "<|reserved_special_token_49|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "128055": {
446
+ "content": "<|reserved_special_token_50|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "128056": {
454
+ "content": "<|reserved_special_token_51|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "128057": {
462
+ "content": "<|reserved_special_token_52|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "128058": {
470
+ "content": "<|reserved_special_token_53|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "128059": {
478
+ "content": "<|reserved_special_token_54|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "128060": {
486
+ "content": "<|reserved_special_token_55|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "128061": {
494
+ "content": "<|reserved_special_token_56|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "128062": {
502
+ "content": "<|reserved_special_token_57|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "128063": {
510
+ "content": "<|reserved_special_token_58|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "128064": {
518
+ "content": "<|reserved_special_token_59|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "128065": {
526
+ "content": "<|reserved_special_token_60|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "128066": {
534
+ "content": "<|reserved_special_token_61|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "128067": {
542
+ "content": "<|reserved_special_token_62|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "128068": {
550
+ "content": "<|reserved_special_token_63|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "128069": {
558
+ "content": "<|reserved_special_token_64|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "128070": {
566
+ "content": "<|reserved_special_token_65|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "128071": {
574
+ "content": "<|reserved_special_token_66|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "128072": {
582
+ "content": "<|reserved_special_token_67|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "128073": {
590
+ "content": "<|reserved_special_token_68|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "128074": {
598
+ "content": "<|reserved_special_token_69|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "128075": {
606
+ "content": "<|reserved_special_token_70|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "128076": {
614
+ "content": "<|reserved_special_token_71|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "128077": {
622
+ "content": "<|reserved_special_token_72|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "128078": {
630
+ "content": "<|reserved_special_token_73|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "128079": {
638
+ "content": "<|reserved_special_token_74|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "128080": {
646
+ "content": "<|reserved_special_token_75|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "128081": {
654
+ "content": "<|reserved_special_token_76|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "128082": {
662
+ "content": "<|reserved_special_token_77|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "128083": {
670
+ "content": "<|reserved_special_token_78|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "128084": {
678
+ "content": "<|reserved_special_token_79|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "128085": {
686
+ "content": "<|reserved_special_token_80|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "128086": {
694
+ "content": "<|reserved_special_token_81|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "128087": {
702
+ "content": "<|reserved_special_token_82|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "128088": {
710
+ "content": "<|reserved_special_token_83|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "128089": {
718
+ "content": "<|reserved_special_token_84|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "128090": {
726
+ "content": "<|reserved_special_token_85|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "128091": {
734
+ "content": "<|reserved_special_token_86|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "128092": {
742
+ "content": "<|reserved_special_token_87|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "128093": {
750
+ "content": "<|reserved_special_token_88|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "128094": {
758
+ "content": "<|reserved_special_token_89|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "128095": {
766
+ "content": "<|reserved_special_token_90|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "128096": {
774
+ "content": "<|reserved_special_token_91|>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "128097": {
782
+ "content": "<|reserved_special_token_92|>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "128098": {
790
+ "content": "<|reserved_special_token_93|>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "128099": {
798
+ "content": "<|reserved_special_token_94|>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "128100": {
806
+ "content": "<|reserved_special_token_95|>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "128101": {
814
+ "content": "<|reserved_special_token_96|>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "128102": {
822
+ "content": "<|reserved_special_token_97|>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "128103": {
830
+ "content": "<|reserved_special_token_98|>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "128104": {
838
+ "content": "<|reserved_special_token_99|>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "128105": {
846
+ "content": "<|reserved_special_token_100|>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "128106": {
854
+ "content": "<|reserved_special_token_101|>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "128107": {
862
+ "content": "<|reserved_special_token_102|>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "128108": {
870
+ "content": "<|reserved_special_token_103|>",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": true
876
+ },
877
+ "128109": {
878
+ "content": "<|reserved_special_token_104|>",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": true
884
+ },
885
+ "128110": {
886
+ "content": "<|reserved_special_token_105|>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": true
892
+ },
893
+ "128111": {
894
+ "content": "<|reserved_special_token_106|>",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": true
900
+ },
901
+ "128112": {
902
+ "content": "<|reserved_special_token_107|>",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": true
908
+ },
909
+ "128113": {
910
+ "content": "<|reserved_special_token_108|>",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": true
916
+ },
917
+ "128114": {
918
+ "content": "<|reserved_special_token_109|>",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": true
924
+ },
925
+ "128115": {
926
+ "content": "<|reserved_special_token_110|>",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": true
932
+ },
933
+ "128116": {
934
+ "content": "<|reserved_special_token_111|>",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": true
940
+ },
941
+ "128117": {
942
+ "content": "<|reserved_special_token_112|>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": true
948
+ },
949
+ "128118": {
950
+ "content": "<|reserved_special_token_113|>",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": true
956
+ },
957
+ "128119": {
958
+ "content": "<|reserved_special_token_114|>",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": true
964
+ },
965
+ "128120": {
966
+ "content": "<|reserved_special_token_115|>",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": true
972
+ },
973
+ "128121": {
974
+ "content": "<|reserved_special_token_116|>",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": true
980
+ },
981
+ "128122": {
982
+ "content": "<|reserved_special_token_117|>",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": true
988
+ },
989
+ "128123": {
990
+ "content": "<|reserved_special_token_118|>",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": true
996
+ },
997
+ "128124": {
998
+ "content": "<|reserved_special_token_119|>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": true
1004
+ },
1005
+ "128125": {
1006
+ "content": "<|reserved_special_token_120|>",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": true
1012
+ },
1013
+ "128126": {
1014
+ "content": "<|reserved_special_token_121|>",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": true
1020
+ },
1021
+ "128127": {
1022
+ "content": "<|reserved_special_token_122|>",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": true
1028
+ },
1029
+ "128128": {
1030
+ "content": "<|reserved_special_token_123|>",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": true
1036
+ },
1037
+ "128129": {
1038
+ "content": "<|reserved_special_token_124|>",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": true
1044
+ },
1045
+ "128130": {
1046
+ "content": "<|reserved_special_token_125|>",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": true
1052
+ },
1053
+ "128131": {
1054
+ "content": "<|reserved_special_token_126|>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": true
1060
+ },
1061
+ "128132": {
1062
+ "content": "<|reserved_special_token_127|>",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": true
1068
+ },
1069
+ "128133": {
1070
+ "content": "<|reserved_special_token_128|>",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": true
1076
+ },
1077
+ "128134": {
1078
+ "content": "<|reserved_special_token_129|>",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": true
1084
+ },
1085
+ "128135": {
1086
+ "content": "<|reserved_special_token_130|>",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": true
1092
+ },
1093
+ "128136": {
1094
+ "content": "<|reserved_special_token_131|>",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": true
1100
+ },
1101
+ "128137": {
1102
+ "content": "<|reserved_special_token_132|>",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": true
1108
+ },
1109
+ "128138": {
1110
+ "content": "<|reserved_special_token_133|>",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": true
1116
+ },
1117
+ "128139": {
1118
+ "content": "<|reserved_special_token_134|>",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": true
1124
+ },
1125
+ "128140": {
1126
+ "content": "<|reserved_special_token_135|>",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": true
1132
+ },
1133
+ "128141": {
1134
+ "content": "<|reserved_special_token_136|>",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": true
1140
+ },
1141
+ "128142": {
1142
+ "content": "<|reserved_special_token_137|>",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": true
1148
+ },
1149
+ "128143": {
1150
+ "content": "<|reserved_special_token_138|>",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": true
1156
+ },
1157
+ "128144": {
1158
+ "content": "<|reserved_special_token_139|>",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": true
1164
+ },
1165
+ "128145": {
1166
+ "content": "<|reserved_special_token_140|>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": true
1172
+ },
1173
+ "128146": {
1174
+ "content": "<|reserved_special_token_141|>",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": true
1180
+ },
1181
+ "128147": {
1182
+ "content": "<|reserved_special_token_142|>",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": true
1188
+ },
1189
+ "128148": {
1190
+ "content": "<|reserved_special_token_143|>",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": true
1196
+ },
1197
+ "128149": {
1198
+ "content": "<|reserved_special_token_144|>",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": true
1204
+ },
1205
+ "128150": {
1206
+ "content": "<|reserved_special_token_145|>",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": true
1212
+ },
1213
+ "128151": {
1214
+ "content": "<|reserved_special_token_146|>",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": true
1220
+ },
1221
+ "128152": {
1222
+ "content": "<|reserved_special_token_147|>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": true
1228
+ },
1229
+ "128153": {
1230
+ "content": "<|reserved_special_token_148|>",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": true
1236
+ },
1237
+ "128154": {
1238
+ "content": "<|reserved_special_token_149|>",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": true
1244
+ },
1245
+ "128155": {
1246
+ "content": "<|reserved_special_token_150|>",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": true
1252
+ },
1253
+ "128156": {
1254
+ "content": "<|reserved_special_token_151|>",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": true
1260
+ },
1261
+ "128157": {
1262
+ "content": "<|reserved_special_token_152|>",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": true
1268
+ },
1269
+ "128158": {
1270
+ "content": "<|reserved_special_token_153|>",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": true
1276
+ },
1277
+ "128159": {
1278
+ "content": "<|reserved_special_token_154|>",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": true
1284
+ },
1285
+ "128160": {
1286
+ "content": "<|reserved_special_token_155|>",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": true
1292
+ },
1293
+ "128161": {
1294
+ "content": "<|reserved_special_token_156|>",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": true
1300
+ },
1301
+ "128162": {
1302
+ "content": "<|reserved_special_token_157|>",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": true
1308
+ },
1309
+ "128163": {
1310
+ "content": "<|reserved_special_token_158|>",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": true
1316
+ },
1317
+ "128164": {
1318
+ "content": "<|reserved_special_token_159|>",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": true
1324
+ },
1325
+ "128165": {
1326
+ "content": "<|reserved_special_token_160|>",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": true
1332
+ },
1333
+ "128166": {
1334
+ "content": "<|reserved_special_token_161|>",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": true
1340
+ },
1341
+ "128167": {
1342
+ "content": "<|reserved_special_token_162|>",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": true
1348
+ },
1349
+ "128168": {
1350
+ "content": "<|reserved_special_token_163|>",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": true
1356
+ },
1357
+ "128169": {
1358
+ "content": "<|reserved_special_token_164|>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": true
1364
+ },
1365
+ "128170": {
1366
+ "content": "<|reserved_special_token_165|>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": true
1372
+ },
1373
+ "128171": {
1374
+ "content": "<|reserved_special_token_166|>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": true
1380
+ },
1381
+ "128172": {
1382
+ "content": "<|reserved_special_token_167|>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": true
1388
+ },
1389
+ "128173": {
1390
+ "content": "<|reserved_special_token_168|>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": true
1396
+ },
1397
+ "128174": {
1398
+ "content": "<|reserved_special_token_169|>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": true
1404
+ },
1405
+ "128175": {
1406
+ "content": "<|reserved_special_token_170|>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": true
1412
+ },
1413
+ "128176": {
1414
+ "content": "<|reserved_special_token_171|>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": true
1420
+ },
1421
+ "128177": {
1422
+ "content": "<|reserved_special_token_172|>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": true
1428
+ },
1429
+ "128178": {
1430
+ "content": "<|reserved_special_token_173|>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": true
1436
+ },
1437
+ "128179": {
1438
+ "content": "<|reserved_special_token_174|>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": true
1444
+ },
1445
+ "128180": {
1446
+ "content": "<|reserved_special_token_175|>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": true
1452
+ },
1453
+ "128181": {
1454
+ "content": "<|reserved_special_token_176|>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": true
1460
+ },
1461
+ "128182": {
1462
+ "content": "<|reserved_special_token_177|>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": true
1468
+ },
1469
+ "128183": {
1470
+ "content": "<|reserved_special_token_178|>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": true
1476
+ },
1477
+ "128184": {
1478
+ "content": "<|reserved_special_token_179|>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": true
1484
+ },
1485
+ "128185": {
1486
+ "content": "<|reserved_special_token_180|>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": true
1492
+ },
1493
+ "128186": {
1494
+ "content": "<|reserved_special_token_181|>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": true
1500
+ },
1501
+ "128187": {
1502
+ "content": "<|reserved_special_token_182|>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": true
1508
+ },
1509
+ "128188": {
1510
+ "content": "<|reserved_special_token_183|>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": true
1516
+ },
1517
+ "128189": {
1518
+ "content": "<|reserved_special_token_184|>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": true
1524
+ },
1525
+ "128190": {
1526
+ "content": "<|reserved_special_token_185|>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": true
1532
+ },
1533
+ "128191": {
1534
+ "content": "<|reserved_special_token_186|>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": true
1540
+ },
1541
+ "128192": {
1542
+ "content": "<|reserved_special_token_187|>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": true
1548
+ },
1549
+ "128193": {
1550
+ "content": "<|reserved_special_token_188|>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": true
1556
+ },
1557
+ "128194": {
1558
+ "content": "<|reserved_special_token_189|>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": true
1564
+ },
1565
+ "128195": {
1566
+ "content": "<|reserved_special_token_190|>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": true
1572
+ },
1573
+ "128196": {
1574
+ "content": "<|reserved_special_token_191|>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": true
1580
+ },
1581
+ "128197": {
1582
+ "content": "<|reserved_special_token_192|>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": true
1588
+ },
1589
+ "128198": {
1590
+ "content": "<|reserved_special_token_193|>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": true
1596
+ },
1597
+ "128199": {
1598
+ "content": "<|reserved_special_token_194|>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": true
1604
+ },
1605
+ "128200": {
1606
+ "content": "<|reserved_special_token_195|>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": true
1612
+ },
1613
+ "128201": {
1614
+ "content": "<|reserved_special_token_196|>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": true
1620
+ },
1621
+ "128202": {
1622
+ "content": "<|reserved_special_token_197|>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": true
1628
+ },
1629
+ "128203": {
1630
+ "content": "<|reserved_special_token_198|>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": true
1636
+ },
1637
+ "128204": {
1638
+ "content": "<|reserved_special_token_199|>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": true
1644
+ },
1645
+ "128205": {
1646
+ "content": "<|reserved_special_token_200|>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": true
1652
+ },
1653
+ "128206": {
1654
+ "content": "<|reserved_special_token_201|>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": true
1660
+ },
1661
+ "128207": {
1662
+ "content": "<|reserved_special_token_202|>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": true
1668
+ },
1669
+ "128208": {
1670
+ "content": "<|reserved_special_token_203|>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": true
1676
+ },
1677
+ "128209": {
1678
+ "content": "<|reserved_special_token_204|>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": true
1684
+ },
1685
+ "128210": {
1686
+ "content": "<|reserved_special_token_205|>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": true
1692
+ },
1693
+ "128211": {
1694
+ "content": "<|reserved_special_token_206|>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": true
1700
+ },
1701
+ "128212": {
1702
+ "content": "<|reserved_special_token_207|>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": true
1708
+ },
1709
+ "128213": {
1710
+ "content": "<|reserved_special_token_208|>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": true
1716
+ },
1717
+ "128214": {
1718
+ "content": "<|reserved_special_token_209|>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": true
1724
+ },
1725
+ "128215": {
1726
+ "content": "<|reserved_special_token_210|>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": true
1732
+ },
1733
+ "128216": {
1734
+ "content": "<|reserved_special_token_211|>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": true
1740
+ },
1741
+ "128217": {
1742
+ "content": "<|reserved_special_token_212|>",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": true
1748
+ },
1749
+ "128218": {
1750
+ "content": "<|reserved_special_token_213|>",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": true
1756
+ },
1757
+ "128219": {
1758
+ "content": "<|reserved_special_token_214|>",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": true
1764
+ },
1765
+ "128220": {
1766
+ "content": "<|reserved_special_token_215|>",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": true
1772
+ },
1773
+ "128221": {
1774
+ "content": "<|reserved_special_token_216|>",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": true
1780
+ },
1781
+ "128222": {
1782
+ "content": "<|reserved_special_token_217|>",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": true
1788
+ },
1789
+ "128223": {
1790
+ "content": "<|reserved_special_token_218|>",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": true
1796
+ },
1797
+ "128224": {
1798
+ "content": "<|reserved_special_token_219|>",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": true
1804
+ },
1805
+ "128225": {
1806
+ "content": "<|reserved_special_token_220|>",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": true
1812
+ },
1813
+ "128226": {
1814
+ "content": "<|reserved_special_token_221|>",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": true
1820
+ },
1821
+ "128227": {
1822
+ "content": "<|reserved_special_token_222|>",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": true
1828
+ },
1829
+ "128228": {
1830
+ "content": "<|reserved_special_token_223|>",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": true
1836
+ },
1837
+ "128229": {
1838
+ "content": "<|reserved_special_token_224|>",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": true
1844
+ },
1845
+ "128230": {
1846
+ "content": "<|reserved_special_token_225|>",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": true
1852
+ },
1853
+ "128231": {
1854
+ "content": "<|reserved_special_token_226|>",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": true
1860
+ },
1861
+ "128232": {
1862
+ "content": "<|reserved_special_token_227|>",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": true
1868
+ },
1869
+ "128233": {
1870
+ "content": "<|reserved_special_token_228|>",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": true
1876
+ },
1877
+ "128234": {
1878
+ "content": "<|reserved_special_token_229|>",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": true
1884
+ },
1885
+ "128235": {
1886
+ "content": "<|reserved_special_token_230|>",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": true
1892
+ },
1893
+ "128236": {
1894
+ "content": "<|reserved_special_token_231|>",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": true
1900
+ },
1901
+ "128237": {
1902
+ "content": "<|reserved_special_token_232|>",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": true
1908
+ },
1909
+ "128238": {
1910
+ "content": "<|reserved_special_token_233|>",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": true
1916
+ },
1917
+ "128239": {
1918
+ "content": "<|reserved_special_token_234|>",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": true
1924
+ },
1925
+ "128240": {
1926
+ "content": "<|reserved_special_token_235|>",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": true
1932
+ },
1933
+ "128241": {
1934
+ "content": "<|reserved_special_token_236|>",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": true
1940
+ },
1941
+ "128242": {
1942
+ "content": "<|reserved_special_token_237|>",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": true
1948
+ },
1949
+ "128243": {
1950
+ "content": "<|reserved_special_token_238|>",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": true
1956
+ },
1957
+ "128244": {
1958
+ "content": "<|reserved_special_token_239|>",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": true
1964
+ },
1965
+ "128245": {
1966
+ "content": "<|reserved_special_token_240|>",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": true
1972
+ },
1973
+ "128246": {
1974
+ "content": "<|reserved_special_token_241|>",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": true
1980
+ },
1981
+ "128247": {
1982
+ "content": "<|reserved_special_token_242|>",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": true
1988
+ },
1989
+ "128248": {
1990
+ "content": "<|reserved_special_token_243|>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": true
1996
+ },
1997
+ "128249": {
1998
+ "content": "<|reserved_special_token_244|>",
1999
+ "lstrip": false,
2000
+ "normalized": false,
2001
+ "rstrip": false,
2002
+ "single_word": false,
2003
+ "special": true
2004
+ },
2005
+ "128250": {
2006
+ "content": "<|reserved_special_token_245|>",
2007
+ "lstrip": false,
2008
+ "normalized": false,
2009
+ "rstrip": false,
2010
+ "single_word": false,
2011
+ "special": true
2012
+ },
2013
+ "128251": {
2014
+ "content": "<|reserved_special_token_246|>",
2015
+ "lstrip": false,
2016
+ "normalized": false,
2017
+ "rstrip": false,
2018
+ "single_word": false,
2019
+ "special": true
2020
+ },
2021
+ "128252": {
2022
+ "content": "<|reserved_special_token_247|>",
2023
+ "lstrip": false,
2024
+ "normalized": false,
2025
+ "rstrip": false,
2026
+ "single_word": false,
2027
+ "special": true
2028
+ },
2029
+ "128253": {
2030
+ "content": "<|reserved_special_token_248|>",
2031
+ "lstrip": false,
2032
+ "normalized": false,
2033
+ "rstrip": false,
2034
+ "single_word": false,
2035
+ "special": true
2036
+ },
2037
+ "128254": {
2038
+ "content": "<|reserved_special_token_249|>",
2039
+ "lstrip": false,
2040
+ "normalized": false,
2041
+ "rstrip": false,
2042
+ "single_word": false,
2043
+ "special": true
2044
+ },
2045
+ "128255": {
2046
+ "content": "<|reserved_special_token_250|>",
2047
+ "lstrip": false,
2048
+ "normalized": false,
2049
+ "rstrip": false,
2050
+ "single_word": false,
2051
+ "special": true
2052
+ },
2053
+ "128256": {
2054
+ "content": "<unk>",
2055
+ "lstrip": false,
2056
+ "normalized": false,
2057
+ "rstrip": false,
2058
+ "single_word": false,
2059
+ "special": true
2060
+ },
2061
+ "128257": {
2062
+ "content": "<s>",
2063
+ "lstrip": false,
2064
+ "normalized": false,
2065
+ "rstrip": false,
2066
+ "single_word": false,
2067
+ "special": true
2068
+ },
2069
+ "128258": {
2070
+ "content": "</s>",
2071
+ "lstrip": false,
2072
+ "normalized": false,
2073
+ "rstrip": false,
2074
+ "single_word": false,
2075
+ "special": true
2076
+ }
2077
+ },
2078
+ "bos_token": "<s>",
2079
+ "clean_up_tokenization_spaces": false,
2080
+ "cls_token": "<s>",
2081
+ "eos_token": "</s>",
2082
+ "legacy": true,
2083
+ "mask_token": "<unk>",
2084
+ "model_max_length": 8192,
2085
+ "pad_token": "</s>",
2086
+ "sep_token": "<s>",
2087
+ "tokenizer_class": "LlamaTokenizerFast",
2088
+ "unk_token": "<unk>",
2089
+ "use_default_system_prompt": false
2090
+ }
upos.py ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from transformers import TokenClassificationPipeline,LlamaModel,LlamaPreTrainedModel
2
+ from transformers.modeling_outputs import TokenClassifierOutput
3
+
4
+ class BellmanFordTokenClassificationPipeline(TokenClassificationPipeline):
5
+ def __init__(self,**kwargs):
6
+ import numpy
7
+ super().__init__(**kwargs)
8
+ x=self.model.config.label2id
9
+ y=[k for k in x if not k.startswith("I-")]
10
+ self.transition=numpy.full((len(x),len(x)),numpy.nan)
11
+ for k,v in x.items():
12
+ for j in ["I-"+k[2:]] if k.startswith("B-") else [k]+y if k.startswith("I-") else y:
13
+ self.transition[v,x[j]]=0
14
+ def check_model_type(self,supported_models):
15
+ pass
16
+ def postprocess(self,model_outputs,**kwargs):
17
+ import numpy
18
+ if "logits" not in model_outputs:
19
+ return self.postprocess(model_outputs[0],**kwargs)
20
+ m=model_outputs["logits"][0].numpy()
21
+ e=numpy.exp(m-numpy.max(m,axis=-1,keepdims=True))
22
+ z=e/e.sum(axis=-1,keepdims=True)
23
+ for i in range(m.shape[0]-1,0,-1):
24
+ m[i-1]+=numpy.nanmax(m[i]+self.transition,axis=1)
25
+ k=[numpy.nanargmax(m[0])]
26
+ for i in range(1,m.shape[0]):
27
+ k.append(numpy.nanargmax(m[i]+self.transition[k[-1]]))
28
+ w=[{"entity":self.model.config.id2label[j],"start":s,"end":e,"score":z[i,j]} for i,((s,e),j) in enumerate(zip(model_outputs["offset_mapping"][0].tolist(),k)) if s<e]
29
+ if "aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]!="none":
30
+ for i,t in reversed(list(enumerate(w))):
31
+ p=t.pop("entity")
32
+ if p.startswith("I-"):
33
+ w[i-1]["score"]=min(w[i-1]["score"],t["score"])
34
+ w[i-1]["end"]=w.pop(i)["end"]
35
+ elif p.startswith("B-"):
36
+ t["entity_group"]=p[2:]
37
+ else:
38
+ t["entity_group"]=p
39
+ for t in w:
40
+ t["text"]=model_outputs["sentence"][t["start"]:t["end"]]
41
+ return w
42
+
43
+ class LlamaForTokenClassification(LlamaPreTrainedModel):
44
+ def __init__(self,config):
45
+ from torch import nn
46
+ super().__init__(config)
47
+ self.num_labels=config.num_labels
48
+ self.model=LlamaModel(config)
49
+ if hasattr(config,"classifier_dropout") and config.classifier_dropout is not None:
50
+ classifier_dropout=config.classifier_dropout
51
+ elif hasattr(config,"hidden_dropout") and config.hidden_dropout is not None:
52
+ classifier_dropout=config.hidden_dropout
53
+ else:
54
+ classifier_dropout=0.1
55
+ self.dropout=nn.Dropout(classifier_dropout)
56
+ self.classifier=nn.Linear(config.hidden_size,config.num_labels)
57
+ self.post_init()
58
+ def get_input_embeddings(self):
59
+ return self.model.embed_tokens
60
+ def set_input_embeddings(self,value):
61
+ self.model.embed_tokens=value
62
+ def forward(self,input_ids=None,past_key_values=None,attention_mask=None,position_ids=None,inputs_embeds=None,labels=None,use_cache=None,output_attentions=None,output_hidden_states=None,return_dict=None):
63
+ return_dict=return_dict if return_dict is not None else self.config.use_return_dict
64
+ transformer_outputs=self.model(input_ids,past_key_values=past_key_values,attention_mask=attention_mask,position_ids=position_ids,inputs_embeds=inputs_embeds,use_cache=use_cache,output_attentions=output_attentions,output_hidden_states=output_hidden_states,return_dict=return_dict)
65
+ hidden_states=transformer_outputs[0]
66
+ hidden_states=self.dropout(hidden_states)
67
+ logits=self.classifier(hidden_states)
68
+ loss=None
69
+ if labels is not None:
70
+ from torch import nn
71
+ loss_fct=nn.CrossEntropyLoss()
72
+ loss=loss_fct(logits.view(-1,self.num_labels),labels.view(-1))
73
+ if not return_dict:
74
+ output=(logits,)+transformer_outputs[2:]
75
+ return ((loss,)+output) if loss is not None else output
76
+ return TokenClassifierOutput(loss=loss,logits=logits,hidden_states=transformer_outputs.hidden_states,attentions=transformer_outputs.attentions)