CDEH commited on
Commit
2f25894
·
verified ·
1 Parent(s): 32eca91

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RagSequenceForGeneration"
4
+ ],
5
+ "dataset": "wiki_dpr",
6
+ "dataset_split": "train",
7
+ "do_deduplication": true,
8
+ "do_marginalize": false,
9
+ "doc_sep": " // ",
10
+ "exclude_bos_score": false,
11
+ "generator": {
12
+ "_name_or_path": "C:/Users/Pandores/Desktop/CS552/mcqa_models/easy_challenge",
13
+ "add_cross_attention": false,
14
+ "architectures": [
15
+ "T5ForConditionalGeneration"
16
+ ],
17
+ "bad_words_ids": null,
18
+ "begin_suppress_tokens": null,
19
+ "bos_token_id": null,
20
+ "chunk_size_feed_forward": 0,
21
+ "classifier_dropout": 0.0,
22
+ "cross_attention_hidden_size": null,
23
+ "d_ff": 2816,
24
+ "d_kv": 64,
25
+ "d_model": 1024,
26
+ "decoder_start_token_id": 0,
27
+ "dense_act_fn": "gelu_new",
28
+ "diversity_penalty": 0.0,
29
+ "do_sample": false,
30
+ "dropout_rate": 0.1,
31
+ "early_stopping": false,
32
+ "encoder_no_repeat_ngram_size": 0,
33
+ "eos_token_id": 1,
34
+ "exponential_decay_length_penalty": null,
35
+ "feed_forward_proj": "gated-gelu",
36
+ "finetuning_task": null,
37
+ "forced_bos_token_id": null,
38
+ "forced_eos_token_id": null,
39
+ "id2label": {
40
+ "0": "LABEL_0",
41
+ "1": "LABEL_1"
42
+ },
43
+ "initializer_factor": 1.0,
44
+ "is_decoder": false,
45
+ "is_encoder_decoder": true,
46
+ "is_gated_act": true,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
+ "layer_norm_epsilon": 1e-06,
52
+ "length_penalty": 1.0,
53
+ "max_length": 20,
54
+ "min_length": 0,
55
+ "model_type": "t5",
56
+ "n_positions": 512,
57
+ "no_repeat_ngram_size": 0,
58
+ "num_beam_groups": 1,
59
+ "num_beams": 1,
60
+ "num_decoder_layers": 24,
61
+ "num_heads": 16,
62
+ "num_layers": 24,
63
+ "num_return_sequences": 1,
64
+ "output_attentions": false,
65
+ "output_hidden_states": false,
66
+ "output_past": true,
67
+ "output_scores": false,
68
+ "pad_token_id": 0,
69
+ "prefix": null,
70
+ "problem_type": null,
71
+ "pruned_heads": {},
72
+ "relative_attention_max_distance": 128,
73
+ "relative_attention_num_buckets": 32,
74
+ "remove_invalid_values": false,
75
+ "repetition_penalty": 1.0,
76
+ "return_dict": true,
77
+ "return_dict_in_generate": false,
78
+ "sep_token_id": null,
79
+ "suppress_tokens": null,
80
+ "task_specific_params": null,
81
+ "temperature": 1.0,
82
+ "tf_legacy_loss": false,
83
+ "tie_encoder_decoder": false,
84
+ "tie_word_embeddings": false,
85
+ "tokenizer_class": null,
86
+ "top_k": 50,
87
+ "top_p": 1.0,
88
+ "torch_dtype": "float32",
89
+ "torchscript": false,
90
+ "typical_p": 1.0,
91
+ "use_bfloat16": false,
92
+ "use_cache": true,
93
+ "vocab_size": 32128
94
+ },
95
+ "index_name": "compressed",
96
+ "index_path": null,
97
+ "is_encoder_decoder": true,
98
+ "label_smoothing": 0.0,
99
+ "max_combined_length": 300,
100
+ "model_type": "rag",
101
+ "n_docs": 5,
102
+ "output_retrieved": false,
103
+ "passages_path": null,
104
+ "question_encoder": {
105
+ "_name_or_path": "facebook/dpr-question_encoder-single-nq-base",
106
+ "add_cross_attention": false,
107
+ "architectures": [
108
+ "DPRQuestionEncoder"
109
+ ],
110
+ "attention_probs_dropout_prob": 0.1,
111
+ "bad_words_ids": null,
112
+ "begin_suppress_tokens": null,
113
+ "bos_token_id": null,
114
+ "chunk_size_feed_forward": 0,
115
+ "cross_attention_hidden_size": null,
116
+ "decoder_start_token_id": null,
117
+ "diversity_penalty": 0.0,
118
+ "do_sample": false,
119
+ "early_stopping": false,
120
+ "encoder_no_repeat_ngram_size": 0,
121
+ "eos_token_id": null,
122
+ "exponential_decay_length_penalty": null,
123
+ "finetuning_task": null,
124
+ "forced_bos_token_id": null,
125
+ "forced_eos_token_id": null,
126
+ "gradient_checkpointing": false,
127
+ "hidden_act": "gelu",
128
+ "hidden_dropout_prob": 0.1,
129
+ "hidden_size": 768,
130
+ "id2label": {
131
+ "0": "LABEL_0",
132
+ "1": "LABEL_1"
133
+ },
134
+ "initializer_range": 0.02,
135
+ "intermediate_size": 3072,
136
+ "is_decoder": false,
137
+ "is_encoder_decoder": false,
138
+ "label2id": {
139
+ "LABEL_0": 0,
140
+ "LABEL_1": 1
141
+ },
142
+ "layer_norm_eps": 1e-12,
143
+ "length_penalty": 1.0,
144
+ "max_length": 20,
145
+ "max_position_embeddings": 512,
146
+ "min_length": 0,
147
+ "model_type": "dpr",
148
+ "no_repeat_ngram_size": 0,
149
+ "num_attention_heads": 12,
150
+ "num_beam_groups": 1,
151
+ "num_beams": 1,
152
+ "num_hidden_layers": 12,
153
+ "num_return_sequences": 1,
154
+ "output_attentions": false,
155
+ "output_hidden_states": false,
156
+ "output_scores": false,
157
+ "pad_token_id": 0,
158
+ "position_embedding_type": "absolute",
159
+ "prefix": null,
160
+ "problem_type": null,
161
+ "projection_dim": 0,
162
+ "pruned_heads": {},
163
+ "remove_invalid_values": false,
164
+ "repetition_penalty": 1.0,
165
+ "return_dict": true,
166
+ "return_dict_in_generate": false,
167
+ "sep_token_id": null,
168
+ "suppress_tokens": null,
169
+ "task_specific_params": null,
170
+ "temperature": 1.0,
171
+ "tf_legacy_loss": false,
172
+ "tie_encoder_decoder": false,
173
+ "tie_word_embeddings": true,
174
+ "tokenizer_class": null,
175
+ "top_k": 50,
176
+ "top_p": 1.0,
177
+ "torch_dtype": null,
178
+ "torchscript": false,
179
+ "type_vocab_size": 2,
180
+ "typical_p": 1.0,
181
+ "use_bfloat16": false,
182
+ "vocab_size": 30522
183
+ },
184
+ "reduce_loss": false,
185
+ "retrieval_batch_size": 8,
186
+ "retrieval_vector_size": 768,
187
+ "title_sep": " / ",
188
+ "torch_dtype": "float32",
189
+ "transformers_version": "4.38.1",
190
+ "use_cache": true,
191
+ "use_dummy_dataset": false,
192
+ "vocab_size": null
193
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.1"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b738953401a03f5475a9e45b0bebbb6d5a8f44b9a4461bfb6afb55a7176b75b6
3
+ size 3568275448
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]",
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[T5_END]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "3": {
20
+ "content": "[T5_START]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "101": {
36
+ "content": "[CLS]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "102": {
44
+ "content": "[SEP]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "103": {
52
+ "content": "[MASK]",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "clean_up_tokenization_spaces": true,
61
+ "cls_token": "[CLS]",
62
+ "do_basic_tokenize": true,
63
+ "do_lower_case": true,
64
+ "mask_token": "[MASK]",
65
+ "model_max_length": 512,
66
+ "never_split": null,
67
+ "pad_token": "[PAD]",
68
+ "sep_token": "[SEP]",
69
+ "strip_accents": null,
70
+ "tokenize_chinese_chars": true,
71
+ "tokenizer_class": "DPRQuestionEncoderTokenizer",
72
+ "unk_token": "[UNK]"
73
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff