michaelrglass commited on
Commit
823f880
1 Parent(s): 897da59

KGI_0 RAG model for KILT zsRE.

Browse files
Files changed (2) hide show
  1. config.json +211 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/rag-token-nq",
3
+ "architectures": [
4
+ "RagTokenForGeneration"
5
+ ],
6
+ "bad_words_ids": [
7
+ [
8
+ 0,
9
+ 0
10
+ ]
11
+ ],
12
+ "bos_token_id": 0,
13
+ "dataset": "wiki_dpr",
14
+ "dataset_split": "train",
15
+ "decoder_start_token_id": 2,
16
+ "do_deduplication": true,
17
+ "do_marginalize": false,
18
+ "doc_sep": " // ",
19
+ "eos_token_id": 2,
20
+ "exclude_bos_score": false,
21
+ "generator": {
22
+ "_name_or_path": "",
23
+ "_num_labels": 3,
24
+ "activation_dropout": 0.0,
25
+ "activation_function": "gelu",
26
+ "add_bias_logits": false,
27
+ "add_cross_attention": false,
28
+ "add_final_layer_norm": false,
29
+ "architectures": [
30
+ "BartForConditionalGeneration"
31
+ ],
32
+ "attention_dropout": 0.0,
33
+ "bad_words_ids": null,
34
+ "bos_token_id": 0,
35
+ "chunk_size_feed_forward": 0,
36
+ "classif_dropout": 0.0,
37
+ "classifier_dropout": 0.0,
38
+ "d_model": 1024,
39
+ "decoder_attention_heads": 16,
40
+ "decoder_ffn_dim": 4096,
41
+ "decoder_layerdrop": 0.0,
42
+ "decoder_layers": 12,
43
+ "decoder_start_token_id": 2,
44
+ "diversity_penalty": 0.0,
45
+ "do_sample": false,
46
+ "dropout": 0.1,
47
+ "early_stopping": false,
48
+ "encoder_attention_heads": 16,
49
+ "encoder_ffn_dim": 4096,
50
+ "encoder_layerdrop": 0.0,
51
+ "encoder_layers": 12,
52
+ "encoder_no_repeat_ngram_size": 0,
53
+ "eos_token_id": 2,
54
+ "extra_pos_embeddings": 2,
55
+ "finetuning_task": null,
56
+ "force_bos_token_to_be_generated": true,
57
+ "gradient_checkpointing": false,
58
+ "id2label": {
59
+ "0": "LABEL_0",
60
+ "1": "LABEL_1",
61
+ "2": "LABEL_2"
62
+ },
63
+ "init_std": 0.02,
64
+ "is_decoder": false,
65
+ "is_encoder_decoder": true,
66
+ "label2id": {
67
+ "LABEL_0": 0,
68
+ "LABEL_1": 1,
69
+ "LABEL_2": 2
70
+ },
71
+ "length_penalty": 1.0,
72
+ "max_length": 20,
73
+ "max_position_embeddings": 1024,
74
+ "min_length": 0,
75
+ "model_type": "bart",
76
+ "no_repeat_ngram_size": 0,
77
+ "normalize_before": false,
78
+ "normalize_embedding": true,
79
+ "num_beam_groups": 1,
80
+ "num_beams": 1,
81
+ "num_hidden_layers": 12,
82
+ "num_return_sequences": 1,
83
+ "output_attentions": false,
84
+ "output_hidden_states": false,
85
+ "output_past": false,
86
+ "output_scores": false,
87
+ "pad_token_id": 1,
88
+ "prefix": null,
89
+ "pruned_heads": {},
90
+ "repetition_penalty": 1.0,
91
+ "return_dict": true,
92
+ "return_dict_in_generate": false,
93
+ "scale_embedding": false,
94
+ "sep_token_id": null,
95
+ "static_position_embeddings": false,
96
+ "task_specific_params": {
97
+ "summarization": {
98
+ "early_stopping": true,
99
+ "length_penalty": 2.0,
100
+ "max_length": 142,
101
+ "min_length": 56,
102
+ "no_repeat_ngram_size": 3,
103
+ "num_beams": 4
104
+ }
105
+ },
106
+ "temperature": 1.0,
107
+ "tie_encoder_decoder": false,
108
+ "tie_word_embeddings": true,
109
+ "tokenizer_class": null,
110
+ "top_k": 50,
111
+ "top_p": 1.0,
112
+ "torchscript": false,
113
+ "transformers_version": "4.3.2",
114
+ "use_bfloat16": false,
115
+ "use_cache": true,
116
+ "vocab_size": 50265,
117
+ "xla_device": null
118
+ },
119
+ "index_name": "legacy",
120
+ "index_path": null,
121
+ "is_encoder_decoder": true,
122
+ "label_smoothing": 0.0,
123
+ "max_combined_length": 300,
124
+ "max_length": 50,
125
+ "min_length": 1,
126
+ "model_type": "rag",
127
+ "n_docs": 5,
128
+ "num_beams": 4,
129
+ "output_retrieved": false,
130
+ "pad_token_id": 1,
131
+ "passages_path": null,
132
+ "question_encoder": {
133
+ "_name_or_path": "",
134
+ "add_cross_attention": false,
135
+ "architectures": [
136
+ "DPRQuestionEncoder"
137
+ ],
138
+ "attention_probs_dropout_prob": 0.1,
139
+ "bad_words_ids": null,
140
+ "bos_token_id": null,
141
+ "chunk_size_feed_forward": 0,
142
+ "decoder_start_token_id": null,
143
+ "diversity_penalty": 0.0,
144
+ "do_sample": false,
145
+ "early_stopping": false,
146
+ "encoder_no_repeat_ngram_size": 0,
147
+ "eos_token_id": null,
148
+ "finetuning_task": null,
149
+ "gradient_checkpointing": false,
150
+ "hidden_act": "gelu",
151
+ "hidden_dropout_prob": 0.1,
152
+ "hidden_size": 768,
153
+ "id2label": {
154
+ "0": "LABEL_0",
155
+ "1": "LABEL_1"
156
+ },
157
+ "initializer_range": 0.02,
158
+ "intermediate_size": 3072,
159
+ "is_decoder": false,
160
+ "is_encoder_decoder": false,
161
+ "label2id": {
162
+ "LABEL_0": 0,
163
+ "LABEL_1": 1
164
+ },
165
+ "layer_norm_eps": 1e-12,
166
+ "length_penalty": 1.0,
167
+ "max_length": 20,
168
+ "max_position_embeddings": 512,
169
+ "min_length": 0,
170
+ "model_type": "dpr",
171
+ "no_repeat_ngram_size": 0,
172
+ "num_attention_heads": 12,
173
+ "num_beam_groups": 1,
174
+ "num_beams": 1,
175
+ "num_hidden_layers": 12,
176
+ "num_return_sequences": 1,
177
+ "output_attentions": false,
178
+ "output_hidden_states": false,
179
+ "output_scores": false,
180
+ "pad_token_id": 0,
181
+ "position_embedding_type": "absolute",
182
+ "prefix": null,
183
+ "projection_dim": 0,
184
+ "pruned_heads": {},
185
+ "repetition_penalty": 1.0,
186
+ "return_dict": false,
187
+ "return_dict_in_generate": false,
188
+ "sep_token_id": null,
189
+ "task_specific_params": null,
190
+ "temperature": 1.0,
191
+ "tie_encoder_decoder": false,
192
+ "tie_word_embeddings": true,
193
+ "tokenizer_class": null,
194
+ "top_k": 50,
195
+ "top_p": 1.0,
196
+ "torchscript": false,
197
+ "transformers_version": "4.3.2",
198
+ "type_vocab_size": 2,
199
+ "use_bfloat16": false,
200
+ "use_cache": true,
201
+ "vocab_size": 30522,
202
+ "xla_device": null
203
+ },
204
+ "reduce_loss": false,
205
+ "retrieval_batch_size": 8,
206
+ "retrieval_vector_size": 768,
207
+ "title_sep": " / ",
208
+ "use_cache": true,
209
+ "use_dummy_dataset": false,
210
+ "vocab_size": null
211
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:525eced98d73b0648728f86e55d507178bc993d5bb696b006285125e753fdbf6
3
+ size 2063617399