Model upload
Browse files- added_tokens.json +1 -0
- config.json +137 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<TURN>": 50265}
|
config.json
ADDED
@@ -0,0 +1,137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allenai/longformer-base-4096",
|
3 |
+
"architectures": [
|
4 |
+
"LongformerForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_mode": "longformer",
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"attention_window": [
|
9 |
+
512,
|
10 |
+
512,
|
11 |
+
512,
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512
|
21 |
+
],
|
22 |
+
"bos_token_id": 0,
|
23 |
+
"classifier_dropout": null,
|
24 |
+
"eos_token_id": 2,
|
25 |
+
"gradient_checkpointing": false,
|
26 |
+
"hidden_act": "gelu",
|
27 |
+
"hidden_dropout_prob": 0.1,
|
28 |
+
"hidden_size": 768,
|
29 |
+
"id2label": {
|
30 |
+
"0": "O",
|
31 |
+
"1": "I-",
|
32 |
+
"10": "Collaborative-Completion",
|
33 |
+
"11": "Conventional-closing",
|
34 |
+
"12": "Conventional-opening",
|
35 |
+
"13": "Declarative-Wh-Question",
|
36 |
+
"14": "Declarative-Yes-No-Question",
|
37 |
+
"15": "Dispreferred-answers",
|
38 |
+
"16": "Downplayer",
|
39 |
+
"17": "Hedge",
|
40 |
+
"18": "Hold-before-answer-agreement",
|
41 |
+
"19": "Maybe-Accept-part",
|
42 |
+
"2": "3rd-party-talk",
|
43 |
+
"20": "Negative-non-no-answers",
|
44 |
+
"21": "No-answers",
|
45 |
+
"22": "Non-verbal",
|
46 |
+
"23": "Offers-Options-Commits",
|
47 |
+
"24": "Open-Question",
|
48 |
+
"25": "Or-Clause",
|
49 |
+
"26": "Other",
|
50 |
+
"27": "Other-answers",
|
51 |
+
"28": "Quotation",
|
52 |
+
"29": "Reject",
|
53 |
+
"3": "Acknowledge-Backchannel",
|
54 |
+
"30": "Repeat-phrase",
|
55 |
+
"31": "Response-Acknowledgement",
|
56 |
+
"32": "Rhetorical-Questions",
|
57 |
+
"33": "Self-talk",
|
58 |
+
"34": "Signal-non-understanding",
|
59 |
+
"35": "Statement-non-opinion",
|
60 |
+
"36": "Statement-opinion",
|
61 |
+
"37": "Summarize/reformulate",
|
62 |
+
"38": "Tag-Question",
|
63 |
+
"39": "Thanking",
|
64 |
+
"4": "Action-directive",
|
65 |
+
"40": "Uninterpretable",
|
66 |
+
"41": "Wh-Question",
|
67 |
+
"42": "Yes-No-Question",
|
68 |
+
"43": "Yes-answers",
|
69 |
+
"5": "Affirmative-non-yes-answers",
|
70 |
+
"6": "Agree-Accept",
|
71 |
+
"7": "Apology",
|
72 |
+
"8": "Appreciation",
|
73 |
+
"9": "Backchannel-in-question-form"
|
74 |
+
},
|
75 |
+
"ignore_attention_mask": false,
|
76 |
+
"initializer_range": 0.02,
|
77 |
+
"intermediate_size": 3072,
|
78 |
+
"label2id": {
|
79 |
+
"3rd-party-talk": 2,
|
80 |
+
"Acknowledge-Backchannel": 3,
|
81 |
+
"Action-directive": 4,
|
82 |
+
"Affirmative-non-yes-answers": 5,
|
83 |
+
"Agree-Accept": 6,
|
84 |
+
"Apology": 7,
|
85 |
+
"Appreciation": 8,
|
86 |
+
"Backchannel-in-question-form": 9,
|
87 |
+
"Collaborative-Completion": 10,
|
88 |
+
"Conventional-closing": 11,
|
89 |
+
"Conventional-opening": 12,
|
90 |
+
"Declarative-Wh-Question": 13,
|
91 |
+
"Declarative-Yes-No-Question": 14,
|
92 |
+
"Dispreferred-answers": 15,
|
93 |
+
"Downplayer": 16,
|
94 |
+
"Hedge": 17,
|
95 |
+
"Hold-before-answer-agreement": 18,
|
96 |
+
"I-": 1,
|
97 |
+
"Maybe-Accept-part": 19,
|
98 |
+
"Negative-non-no-answers": 20,
|
99 |
+
"No-answers": 21,
|
100 |
+
"Non-verbal": 22,
|
101 |
+
"O": 0,
|
102 |
+
"Offers-Options-Commits": 23,
|
103 |
+
"Open-Question": 24,
|
104 |
+
"Or-Clause": 25,
|
105 |
+
"Other": 26,
|
106 |
+
"Other-answers": 27,
|
107 |
+
"Quotation": 28,
|
108 |
+
"Reject": 29,
|
109 |
+
"Repeat-phrase": 30,
|
110 |
+
"Response-Acknowledgement": 31,
|
111 |
+
"Rhetorical-Questions": 32,
|
112 |
+
"Self-talk": 33,
|
113 |
+
"Signal-non-understanding": 34,
|
114 |
+
"Statement-non-opinion": 35,
|
115 |
+
"Statement-opinion": 36,
|
116 |
+
"Summarize/reformulate": 37,
|
117 |
+
"Tag-Question": 38,
|
118 |
+
"Thanking": 39,
|
119 |
+
"Uninterpretable": 40,
|
120 |
+
"Wh-Question": 41,
|
121 |
+
"Yes-No-Question": 42,
|
122 |
+
"Yes-answers": 43
|
123 |
+
},
|
124 |
+
"layer_norm_eps": 1e-05,
|
125 |
+
"max_position_embeddings": 4098,
|
126 |
+
"model_type": "longformer",
|
127 |
+
"num_attention_heads": 12,
|
128 |
+
"num_hidden_layers": 12,
|
129 |
+
"pad_token_id": 1,
|
130 |
+
"position_embedding_type": "absolute",
|
131 |
+
"sep_token_id": 2,
|
132 |
+
"torch_dtype": "float32",
|
133 |
+
"transformers_version": "4.16.2",
|
134 |
+
"type_vocab_size": 1,
|
135 |
+
"use_cache": true,
|
136 |
+
"vocab_size": 50266
|
137 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ac31bdfa8f8279e43539f570001fdbf2eaa61f4a42db79c718123400784e266
|
3 |
+
size 592551841
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}, "additional_special_tokens": ["<TURN>"]}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 4096, "special_tokens_map_file": null, "name_or_path": "allenai/longformer-base-4096", "tokenizer_class": "LongformerTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|