push
Browse files- config.json +185 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,185 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "metamong1/bigbird-tapt-ep3",
|
3 |
+
"architectures": [
|
4 |
+
"EncoderDecoderModel"
|
5 |
+
],
|
6 |
+
"decoder": {
|
7 |
+
"_name_or_path": "gogamza/kobart-base-v1",
|
8 |
+
"activation_dropout": 0.0,
|
9 |
+
"activation_function": "gelu",
|
10 |
+
"add_bias_logits": false,
|
11 |
+
"add_cross_attention": true,
|
12 |
+
"add_final_layer_norm": false,
|
13 |
+
"architectures": [
|
14 |
+
"BartModel"
|
15 |
+
],
|
16 |
+
"attention_dropout": 0.0,
|
17 |
+
"author": "Heewon Jeon(madjakarta@gmail.com)",
|
18 |
+
"bad_words_ids": null,
|
19 |
+
"bos_token_id": 0,
|
20 |
+
"chunk_size_feed_forward": 0,
|
21 |
+
"classif_dropout": 0.1,
|
22 |
+
"classifier_dropout": 0.1,
|
23 |
+
"d_model": 768,
|
24 |
+
"decoder_attention_heads": 16,
|
25 |
+
"decoder_ffn_dim": 3072,
|
26 |
+
"decoder_layerdrop": 0.0,
|
27 |
+
"decoder_layers": 6,
|
28 |
+
"decoder_start_token_id": 1,
|
29 |
+
"diversity_penalty": 0.0,
|
30 |
+
"do_blenderbot_90_layernorm": false,
|
31 |
+
"do_sample": false,
|
32 |
+
"doc_type_size": 4,
|
33 |
+
"dropout": 0.1,
|
34 |
+
"early_stopping": false,
|
35 |
+
"encoder_attention_heads": 16,
|
36 |
+
"encoder_ffn_dim": 3072,
|
37 |
+
"encoder_layerdrop": 0.0,
|
38 |
+
"encoder_layers": 6,
|
39 |
+
"encoder_no_repeat_ngram_size": 0,
|
40 |
+
"eos_token_id": 1,
|
41 |
+
"extra_pos_embeddings": 2,
|
42 |
+
"finetuning_task": null,
|
43 |
+
"force_bos_token_to_be_generated": false,
|
44 |
+
"forced_bos_token_id": null,
|
45 |
+
"forced_eos_token_id": 1,
|
46 |
+
"gradient_checkpointing": false,
|
47 |
+
"id2label": {
|
48 |
+
"0": "NEGATIVE",
|
49 |
+
"1": "POSITIVE"
|
50 |
+
},
|
51 |
+
"init_std": 0.02,
|
52 |
+
"is_decoder": true,
|
53 |
+
"is_encoder_decoder": true,
|
54 |
+
"kobart_version": 1.0,
|
55 |
+
"label2id": {
|
56 |
+
"NEGATIVE": 0,
|
57 |
+
"POSITIVE": 1
|
58 |
+
},
|
59 |
+
"length_penalty": 1.0,
|
60 |
+
"max_length": 20,
|
61 |
+
"max_position_embeddings": 2048,
|
62 |
+
"min_length": 0,
|
63 |
+
"model_type": "bart",
|
64 |
+
"no_repeat_ngram_size": 0,
|
65 |
+
"normalize_before": false,
|
66 |
+
"normalize_embedding": true,
|
67 |
+
"num_beam_groups": 1,
|
68 |
+
"num_beams": 1,
|
69 |
+
"num_hidden_layers": 6,
|
70 |
+
"num_return_sequences": 1,
|
71 |
+
"output_attentions": false,
|
72 |
+
"output_hidden_states": false,
|
73 |
+
"output_scores": false,
|
74 |
+
"pad_token_id": 0,
|
75 |
+
"prefix": null,
|
76 |
+
"problem_type": null,
|
77 |
+
"pruned_heads": {},
|
78 |
+
"remove_invalid_values": false,
|
79 |
+
"repetition_penalty": 1.0,
|
80 |
+
"return_dict": true,
|
81 |
+
"return_dict_in_generate": false,
|
82 |
+
"scale_embedding": false,
|
83 |
+
"sep_token_id": null,
|
84 |
+
"static_position_embeddings": false,
|
85 |
+
"task_specific_params": null,
|
86 |
+
"temperature": 1.0,
|
87 |
+
"tie_encoder_decoder": false,
|
88 |
+
"tie_word_embeddings": true,
|
89 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
90 |
+
"top_k": 50,
|
91 |
+
"top_p": 1.0,
|
92 |
+
"torch_dtype": null,
|
93 |
+
"torchscript": false,
|
94 |
+
"transformers_version": "4.11.0",
|
95 |
+
"use_bfloat16": false,
|
96 |
+
"use_cache": true,
|
97 |
+
"vocab_size": 32500
|
98 |
+
},
|
99 |
+
"encoder": {
|
100 |
+
"_name_or_path": "monologg/kobigbird-bert-base",
|
101 |
+
"add_cross_attention": false,
|
102 |
+
"architectures": [
|
103 |
+
"BigBirdForMaskedLM"
|
104 |
+
],
|
105 |
+
"attention_probs_dropout_prob": 0.1,
|
106 |
+
"attention_type": "block_sparse",
|
107 |
+
"bad_words_ids": null,
|
108 |
+
"block_size": 64,
|
109 |
+
"bos_token_id": 5,
|
110 |
+
"chunk_size_feed_forward": 0,
|
111 |
+
"classifier_dropout": null,
|
112 |
+
"decoder_start_token_id": null,
|
113 |
+
"diversity_penalty": 0.0,
|
114 |
+
"do_sample": false,
|
115 |
+
"doc_type_size": 4,
|
116 |
+
"early_stopping": false,
|
117 |
+
"encoder_no_repeat_ngram_size": 0,
|
118 |
+
"eos_token_id": 6,
|
119 |
+
"finetuning_task": null,
|
120 |
+
"forced_bos_token_id": null,
|
121 |
+
"forced_eos_token_id": null,
|
122 |
+
"gradient_checkpointing": false,
|
123 |
+
"hidden_act": "gelu_new",
|
124 |
+
"hidden_dropout_prob": 0.1,
|
125 |
+
"hidden_size": 768,
|
126 |
+
"id2label": {
|
127 |
+
"0": "LABEL_0",
|
128 |
+
"1": "LABEL_1"
|
129 |
+
},
|
130 |
+
"initializer_range": 0.02,
|
131 |
+
"intermediate_size": 3072,
|
132 |
+
"is_decoder": false,
|
133 |
+
"is_encoder_decoder": false,
|
134 |
+
"label2id": {
|
135 |
+
"LABEL_0": 0,
|
136 |
+
"LABEL_1": 1
|
137 |
+
},
|
138 |
+
"layer_norm_eps": 1e-12,
|
139 |
+
"length_penalty": 1.0,
|
140 |
+
"max_length": 20,
|
141 |
+
"max_position_embeddings": 4096,
|
142 |
+
"min_length": 0,
|
143 |
+
"model_type": "big_bird",
|
144 |
+
"no_repeat_ngram_size": 0,
|
145 |
+
"num_attention_heads": 12,
|
146 |
+
"num_beam_groups": 1,
|
147 |
+
"num_beams": 1,
|
148 |
+
"num_hidden_layers": 6,
|
149 |
+
"num_random_blocks": 3,
|
150 |
+
"num_return_sequences": 1,
|
151 |
+
"output_attentions": false,
|
152 |
+
"output_hidden_states": false,
|
153 |
+
"output_scores": false,
|
154 |
+
"pad_token_id": 0,
|
155 |
+
"position_embedding_type": "absolute",
|
156 |
+
"prefix": null,
|
157 |
+
"problem_type": null,
|
158 |
+
"pruned_heads": {},
|
159 |
+
"remove_invalid_values": false,
|
160 |
+
"repetition_penalty": 1.0,
|
161 |
+
"rescale_embeddings": false,
|
162 |
+
"return_dict": true,
|
163 |
+
"return_dict_in_generate": false,
|
164 |
+
"sep_token_id": 3,
|
165 |
+
"task_specific_params": null,
|
166 |
+
"temperature": 1.0,
|
167 |
+
"tie_encoder_decoder": false,
|
168 |
+
"tie_word_embeddings": true,
|
169 |
+
"tokenizer_class": "BertTokenizer",
|
170 |
+
"top_k": 50,
|
171 |
+
"top_p": 1.0,
|
172 |
+
"torch_dtype": "float32",
|
173 |
+
"torchscript": false,
|
174 |
+
"transformers_version": "4.11.0",
|
175 |
+
"type_vocab_size": 2,
|
176 |
+
"use_bfloat16": false,
|
177 |
+
"use_bias": true,
|
178 |
+
"use_cache": true,
|
179 |
+
"vocab_size": 32500
|
180 |
+
},
|
181 |
+
"is_encoder_decoder": true,
|
182 |
+
"model_type": "encoder-decoder",
|
183 |
+
"torch_dtype": "float32",
|
184 |
+
"transformers_version": null
|
185 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c78ab7d24da74b066daf097c03b5bae8ea8ff619e5c18a508fafc8f5ea039ee8
|
3 |
+
size 718021289
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "bos_token": "<s>", "eos_token": "</s>", "model_max_length": 4096, "special_tokens_map_file": "/opt/ml/.cache/huggingface/transformers/9bea998b48658e35dd618115a266f6c173183a9a4261fc6e40730d74c4b67899.e3640e465e51ce85d94923a0b396029ecc2e3e4c7764031eee57ab272637652d", "name_or_path": "metamong1/bigbird-tapt-ep3", "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|