tmills commited on
Commit
896cd60
1 Parent(s): 86cf823

Updated for latest version of cnlpt.

Browse files
Files changed (4) hide show
  1. added_tokens.json +1 -1
  2. config.json +92 -20
  3. pytorch_model.bin +1 -1
  4. tokenizer_config.json +1 -1
added_tokens.json CHANGED
@@ -1 +1 @@
1
- {"<a1>": 50267, "<cr>": 50271, "</a1>": 50268, "<e>": 50265, "</e>": 50266, "<neg>": 50272, "<a2>": 50269, "</a2>": 50270}
 
1
+ {"</a2>": 50270, "</e>": 50266, "</a1>": 50268, "<cr>": 50271, "<e>": 50265, "<a2>": 50269, "<a1>": 50267, "<neg>": 50272}
config.json CHANGED
@@ -1,34 +1,106 @@
1
  {
2
- "_name_or_path": "roberta-base",
3
  "architectures": [
4
- "CnlpRobertaForClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "bos_token_id": 0,
8
- "eos_token_id": 2,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "finetuning_task": [
10
  "event"
11
  ],
12
- "freeze": false,
13
- "gradient_checkpointing": false,
14
- "hidden_act": "gelu",
15
  "hidden_dropout_prob": 0.1,
16
  "hidden_size": 768,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 3072,
19
  "layer": 11,
20
- "layer_norm_eps": 1e-05,
21
- "max_position_embeddings": 514,
22
- "model_type": "roberta",
23
- "num_attention_heads": 12,
24
- "num_hidden_layers": 12,
25
  "num_rel_attention_heads": 12,
26
- "pad_token_id": 1,
27
- "position_embedding_type": "absolute",
28
  "rel_attention_head_dims": 64,
 
 
 
 
 
 
29
  "tokens": false,
30
- "transformers_version": "4.4.2",
31
- "type_vocab_size": 1,
32
- "use_cache": true,
33
  "vocab_size": 50273
34
  }
 
1
  {
 
2
  "architectures": [
3
+ "CnlpModelForClassification"
4
  ],
5
+ "encoder_config": {
6
+ "_name_or_path": "roberta-base",
7
+ "add_cross_attention": false,
8
+ "architectures": [
9
+ "RobertaForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": 0,
14
+ "chunk_size_feed_forward": 0,
15
+ "classifier_dropout": null,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": 2,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "is_decoder": false,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_eps": 1e-05,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "max_position_embeddings": 514,
45
+ "min_length": 0,
46
+ "model_type": "roberta",
47
+ "no_repeat_ngram_size": 0,
48
+ "num_attention_heads": 12,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_hidden_layers": 12,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": 1,
57
+ "position_embedding_type": "absolute",
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "sep_token_id": null,
66
+ "task_specific_params": null,
67
+ "temperature": 1.0,
68
+ "tie_encoder_decoder": false,
69
+ "tie_word_embeddings": true,
70
+ "tokenizer_class": null,
71
+ "top_k": 50,
72
+ "top_p": 1.0,
73
+ "torch_dtype": null,
74
+ "torchscript": false,
75
+ "transformers_version": "4.15.0",
76
+ "type_vocab_size": 1,
77
+ "use_bfloat16": false,
78
+ "use_cache": true,
79
+ "vocab_size": 50273
80
+ },
81
+ "encoder_name": "roberta-base",
82
  "finetuning_task": [
83
  "event"
84
  ],
 
 
 
85
  "hidden_dropout_prob": 0.1,
86
  "hidden_size": 768,
 
 
87
  "layer": 11,
88
+ "model_type": "cnlpt",
89
+ "num_labels_list": [
90
+ 9
91
+ ],
 
92
  "num_rel_attention_heads": 12,
93
+ "num_tokens": -1,
 
94
  "rel_attention_head_dims": 64,
95
+ "relations": [
96
+ false
97
+ ],
98
+ "tagger": [
99
+ true
100
+ ],
101
  "tokens": false,
102
+ "torch_dtype": "float32",
103
+ "transformers_version": "4.15.0",
104
+ "use_prior_tasks": false,
105
  "vocab_size": 50273
106
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a67fffd8017200ed128cf604d230dd213be714e71f5cd6501852010967f0397
3
  size 501053685
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e16d688f18fd8fbebbd954059aa74f99578c49d2210566ada92a5332f14c6ef2
3
  size 501053685
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "additional_special_tokens": ["<e>", "</e>", "<a1>", "</a1>", "<a2>", "</a2>", "<cr>", "<neg>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base"}
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "additional_special_tokens": ["<e>", "</e>", "<a1>", "</a1>", "<a2>", "</a2>", "<cr>", "<neg>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}