Pragformer
commited on
Commit
•
af0032a
1
Parent(s):
3d66b0e
Upload BERT_Arch
Browse files- config.json +123 -26
- pytorch_model.bin +1 -1
config.json
CHANGED
@@ -1,33 +1,130 @@
|
|
1 |
{
|
2 |
"_name_or_path": "./PragFormer",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
"
|
16 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
},
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"model_type": "bert",
|
24 |
-
"num_attention_heads": 12,
|
25 |
-
"num_hidden_layers": 12,
|
26 |
-
"pad_token_id": 1,
|
27 |
-
"position_embedding_type": "absolute",
|
28 |
"torch_dtype": "float32",
|
29 |
-
"transformers_version": "4.25.1"
|
30 |
-
"type_vocab_size": 1,
|
31 |
-
"use_cache": true,
|
32 |
-
"vocab_size": 50265
|
33 |
}
|
|
|
1 |
{
|
2 |
"_name_or_path": "./PragFormer",
|
3 |
"architectures": [
|
4 |
+
"BERT_Arch"
|
5 |
],
|
6 |
+
"bert": {
|
7 |
+
"_commit_hash": "43cf2d48e8c75d255dccab2a19e40d4774fd8853",
|
8 |
+
"_name_or_path": "NTUYG/DeepSCC-RoBERTa",
|
9 |
+
"add_cross_attention": false,
|
10 |
+
"architectures": [
|
11 |
+
"RobertaForSequenceClassification"
|
12 |
+
],
|
13 |
+
"attention_probs_dropout_prob": 0.1,
|
14 |
+
"bad_words_ids": null,
|
15 |
+
"begin_suppress_tokens": null,
|
16 |
+
"bos_token_id": 0,
|
17 |
+
"chunk_size_feed_forward": 0,
|
18 |
+
"classifier_dropout": null,
|
19 |
+
"cross_attention_hidden_size": null,
|
20 |
+
"decoder_start_token_id": null,
|
21 |
+
"diversity_penalty": 0.0,
|
22 |
+
"do_sample": false,
|
23 |
+
"early_stopping": false,
|
24 |
+
"encoder_no_repeat_ngram_size": 0,
|
25 |
+
"eos_token_id": 2,
|
26 |
+
"exponential_decay_length_penalty": null,
|
27 |
+
"finetuning_task": null,
|
28 |
+
"forced_bos_token_id": null,
|
29 |
+
"forced_eos_token_id": null,
|
30 |
+
"gradient_checkpointing": false,
|
31 |
+
"hidden_act": "gelu",
|
32 |
+
"hidden_dropout_prob": 0.1,
|
33 |
+
"hidden_size": 768,
|
34 |
+
"id2label": {
|
35 |
+
"0": "LABEL_0",
|
36 |
+
"1": "LABEL_1",
|
37 |
+
"10": "LABEL_10",
|
38 |
+
"11": "LABEL_11",
|
39 |
+
"12": "LABEL_12",
|
40 |
+
"13": "LABEL_13",
|
41 |
+
"14": "LABEL_14",
|
42 |
+
"15": "LABEL_15",
|
43 |
+
"16": "LABEL_16",
|
44 |
+
"17": "LABEL_17",
|
45 |
+
"18": "LABEL_18",
|
46 |
+
"2": "LABEL_2",
|
47 |
+
"3": "LABEL_3",
|
48 |
+
"4": "LABEL_4",
|
49 |
+
"5": "LABEL_5",
|
50 |
+
"6": "LABEL_6",
|
51 |
+
"7": "LABEL_7",
|
52 |
+
"8": "LABEL_8",
|
53 |
+
"9": "LABEL_9"
|
54 |
+
},
|
55 |
+
"initializer_range": 0.02,
|
56 |
+
"intermediate_size": 3072,
|
57 |
+
"is_decoder": false,
|
58 |
+
"is_encoder_decoder": false,
|
59 |
+
"label2id": {
|
60 |
+
"LABEL_0": 0,
|
61 |
+
"LABEL_1": 1,
|
62 |
+
"LABEL_10": 10,
|
63 |
+
"LABEL_11": 11,
|
64 |
+
"LABEL_12": 12,
|
65 |
+
"LABEL_13": 13,
|
66 |
+
"LABEL_14": 14,
|
67 |
+
"LABEL_15": 15,
|
68 |
+
"LABEL_16": 16,
|
69 |
+
"LABEL_17": 17,
|
70 |
+
"LABEL_18": 18,
|
71 |
+
"LABEL_2": 2,
|
72 |
+
"LABEL_3": 3,
|
73 |
+
"LABEL_4": 4,
|
74 |
+
"LABEL_5": 5,
|
75 |
+
"LABEL_6": 6,
|
76 |
+
"LABEL_7": 7,
|
77 |
+
"LABEL_8": 8,
|
78 |
+
"LABEL_9": 9
|
79 |
+
},
|
80 |
+
"layer_norm_eps": 1e-05,
|
81 |
+
"length_penalty": 1.0,
|
82 |
+
"max_length": 20,
|
83 |
+
"max_position_embeddings": 514,
|
84 |
+
"min_length": 0,
|
85 |
+
"model_type": "roberta",
|
86 |
+
"no_repeat_ngram_size": 0,
|
87 |
+
"num_attention_heads": 12,
|
88 |
+
"num_beam_groups": 1,
|
89 |
+
"num_beams": 1,
|
90 |
+
"num_hidden_layers": 12,
|
91 |
+
"num_return_sequences": 1,
|
92 |
+
"output_attentions": false,
|
93 |
+
"output_hidden_states": false,
|
94 |
+
"output_scores": false,
|
95 |
+
"pad_token_id": 1,
|
96 |
+
"position_embedding_type": "absolute",
|
97 |
+
"prefix": null,
|
98 |
+
"problem_type": null,
|
99 |
+
"pruned_heads": {},
|
100 |
+
"remove_invalid_values": false,
|
101 |
+
"repetition_penalty": 1.0,
|
102 |
+
"return_dict": true,
|
103 |
+
"return_dict_in_generate": false,
|
104 |
+
"sep_token_id": null,
|
105 |
+
"suppress_tokens": null,
|
106 |
+
"task_specific_params": null,
|
107 |
+
"temperature": 1.0,
|
108 |
+
"tf_legacy_loss": false,
|
109 |
+
"tie_encoder_decoder": false,
|
110 |
+
"tie_word_embeddings": true,
|
111 |
+
"tokenizer_class": null,
|
112 |
+
"top_k": 50,
|
113 |
+
"top_p": 1.0,
|
114 |
+
"torch_dtype": null,
|
115 |
+
"torchscript": false,
|
116 |
+
"transformers_version": "4.2.0",
|
117 |
+
"type_vocab_size": 1,
|
118 |
+
"typical_p": 1.0,
|
119 |
+
"use_bfloat16": false,
|
120 |
+
"use_cache": true,
|
121 |
+
"vocab_size": 50265
|
122 |
},
|
123 |
+
"dropout": 0.2,
|
124 |
+
"fc1": 512,
|
125 |
+
"fc2": 2,
|
126 |
+
"model_type": "pragformer",
|
127 |
+
"softmax_dim": 1,
|
|
|
|
|
|
|
|
|
|
|
128 |
"torch_dtype": "float32",
|
129 |
+
"transformers_version": "4.25.1"
|
|
|
|
|
|
|
130 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 500230377
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fb600de29d8560f50312dbb80beb10998f91e405fc72f7c17b96862b700433c
|
3 |
size 500230377
|