Oscar066 commited on
Commit
deaf648
·
verified ·
1 Parent(s): 893bdfd

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -1,222 +1,25 @@
1
  {
2
- "_name_or_path": "rag-end2end-retriever/model_checkpoints2/checkpoint83",
3
  "architectures": [
4
- "RagTokenForGeneration"
5
  ],
6
- "dataset": "wiki_dpr",
7
- "dataset_revision": null,
8
- "dataset_split": "train",
9
- "do_deduplication": true,
10
- "do_marginalize": false,
11
- "doc_sep": " // ",
12
- "exclude_bos_score": false,
13
- "forced_eos_token_id": 2,
14
- "generator": {
15
- "_name_or_path": "",
16
- "_num_labels": 3,
17
- "activation_dropout": 0.0,
18
- "activation_function": "gelu",
19
- "add_bias_logits": false,
20
- "add_cross_attention": false,
21
- "add_final_layer_norm": false,
22
- "architectures": [
23
- "BartModel",
24
- "BartForMaskedLM",
25
- "BartForSequenceClassification"
26
- ],
27
- "attention_dropout": 0.1,
28
- "bad_words_ids": null,
29
- "begin_suppress_tokens": null,
30
- "bos_token_id": 0,
31
- "chunk_size_feed_forward": 0,
32
- "classif_dropout": 0.0,
33
- "classifier_dropout": 0.0,
34
- "cross_attention_hidden_size": null,
35
- "d_model": 1024,
36
- "decoder_attention_heads": 16,
37
- "decoder_ffn_dim": 4096,
38
- "decoder_layerdrop": 0.0,
39
- "decoder_layers": 12,
40
- "decoder_start_token_id": 2,
41
- "diversity_penalty": 0.0,
42
- "do_sample": false,
43
- "dropout": 0.1,
44
- "early_stopping": false,
45
- "encoder_attention_heads": 16,
46
- "encoder_ffn_dim": 4096,
47
- "encoder_layerdrop": 0.0,
48
- "encoder_layers": 12,
49
- "encoder_no_repeat_ngram_size": 0,
50
- "eos_token_id": 2,
51
- "exponential_decay_length_penalty": null,
52
- "extra_pos_embeddings": 2,
53
- "finetuning_task": null,
54
- "force_bos_token_to_be_generated": false,
55
- "forced_bos_token_id": null,
56
- "forced_eos_token_id": 2,
57
- "id2label": {
58
- "0": "LABEL_0",
59
- "1": "LABEL_1",
60
- "2": "LABEL_2"
61
- },
62
- "init_std": 0.02,
63
- "is_decoder": false,
64
- "is_encoder_decoder": true,
65
- "label2id": {
66
- "LABEL_0": 0,
67
- "LABEL_1": 1,
68
- "LABEL_2": 2
69
- },
70
- "length_penalty": 1.0,
71
- "max_length": 20,
72
- "max_position_embeddings": 1024,
73
- "min_length": 0,
74
- "model_type": "bart",
75
- "no_repeat_ngram_size": 0,
76
- "normalize_before": false,
77
- "normalize_embedding": true,
78
- "num_beam_groups": 1,
79
- "num_beams": 1,
80
- "num_hidden_layers": 12,
81
- "num_return_sequences": 1,
82
- "output_attentions": false,
83
- "output_hidden_states": false,
84
- "output_past": false,
85
- "output_scores": false,
86
- "pad_token_id": 1,
87
- "prefix": " ",
88
- "problem_type": null,
89
- "pruned_heads": {},
90
- "remove_invalid_values": false,
91
- "repetition_penalty": 1.0,
92
- "return_dict": false,
93
- "return_dict_in_generate": false,
94
- "scale_embedding": false,
95
- "sep_token_id": null,
96
- "static_position_embeddings": false,
97
- "suppress_tokens": null,
98
- "task_specific_params": {
99
- "summarization": {
100
- "early_stopping": true,
101
- "length_penalty": 2.0,
102
- "max_length": 142,
103
- "min_length": 56,
104
- "no_repeat_ngram_size": 3,
105
- "num_beams": 4
106
- }
107
- },
108
- "temperature": 1.0,
109
- "tf_legacy_loss": false,
110
- "tie_encoder_decoder": false,
111
- "tie_word_embeddings": true,
112
- "tokenizer_class": null,
113
- "top_k": 50,
114
- "top_p": 1.0,
115
- "torch_dtype": null,
116
- "torchscript": false,
117
- "typical_p": 1.0,
118
- "use_bfloat16": false,
119
- "use_cache": true,
120
- "vocab_size": 50265
121
- },
122
- "index_name": "custom",
123
- "index_path": "rag-end2end-retriever/Health-data/health-data/my_knowledge_dataset_hnsw_index.faiss",
124
- "is_encoder_decoder": true,
125
- "label_smoothing": 0.1,
126
- "max_combined_length": 300,
127
- "model_type": "rag",
128
- "n_docs": 5,
129
- "output_retrieved": false,
130
- "passages_path": "rag-end2end-retriever/Health-data/health-data/my_knowledge_dataset",
131
- "question_encoder": {
132
- "_name_or_path": "",
133
- "add_cross_attention": false,
134
- "architectures": [
135
- "DPRQuestionEncoder"
136
- ],
137
- "attention_probs_dropout_prob": 0.1,
138
- "bad_words_ids": null,
139
- "begin_suppress_tokens": null,
140
- "bos_token_id": null,
141
- "chunk_size_feed_forward": 0,
142
- "cross_attention_hidden_size": null,
143
- "decoder_start_token_id": null,
144
- "diversity_penalty": 0.0,
145
- "do_sample": false,
146
- "early_stopping": false,
147
- "encoder_no_repeat_ngram_size": 0,
148
- "eos_token_id": null,
149
- "exponential_decay_length_penalty": null,
150
- "finetuning_task": null,
151
- "forced_bos_token_id": null,
152
- "forced_eos_token_id": null,
153
- "gradient_checkpointing": false,
154
- "hidden_act": "gelu",
155
- "hidden_dropout_prob": 0.1,
156
- "hidden_size": 768,
157
- "id2label": {
158
- "0": "LABEL_0",
159
- "1": "LABEL_1"
160
- },
161
- "initializer_range": 0.02,
162
- "intermediate_size": 3072,
163
- "is_decoder": false,
164
- "is_encoder_decoder": false,
165
- "label2id": {
166
- "LABEL_0": 0,
167
- "LABEL_1": 1
168
- },
169
- "layer_norm_eps": 1e-12,
170
- "length_penalty": 1.0,
171
- "max_length": 20,
172
- "max_position_embeddings": 512,
173
- "min_length": 0,
174
- "model_type": "dpr",
175
- "no_repeat_ngram_size": 0,
176
- "num_attention_heads": 12,
177
- "num_beam_groups": 1,
178
- "num_beams": 1,
179
- "num_hidden_layers": 12,
180
- "num_return_sequences": 1,
181
- "output_attentions": false,
182
- "output_hidden_states": false,
183
- "output_scores": false,
184
- "pad_token_id": 0,
185
- "position_embedding_type": "absolute",
186
- "prefix": null,
187
- "problem_type": null,
188
- "projection_dim": 0,
189
- "pruned_heads": {},
190
- "remove_invalid_values": false,
191
- "repetition_penalty": 1.0,
192
- "return_dict": false,
193
- "return_dict_in_generate": false,
194
- "sep_token_id": null,
195
- "suppress_tokens": null,
196
- "task_specific_params": null,
197
- "temperature": 1.0,
198
- "tf_legacy_loss": false,
199
- "tie_encoder_decoder": false,
200
- "tie_word_embeddings": true,
201
- "tokenizer_class": null,
202
- "top_k": 50,
203
- "top_p": 1.0,
204
- "torch_dtype": null,
205
- "torchscript": false,
206
- "type_vocab_size": 2,
207
- "typical_p": 1.0,
208
- "use_bfloat16": false,
209
- "use_cache": true,
210
- "vocab_size": 30522
211
- },
212
- "reduce_loss": false,
213
- "retrieval_batch_size": 8,
214
- "retrieval_vector_size": 768,
215
- "save_step": 83,
216
- "title_sep": " / ",
217
  "torch_dtype": "float32",
218
  "transformers_version": "4.41.0",
219
- "use_cache": true,
220
- "use_dummy_dataset": false,
221
- "vocab_size": null
222
  }
 
1
  {
2
+ "_name_or_path": "facebook/dpr-ctx_encoder-multiset-base",
3
  "architectures": [
4
+ "DPRContextEncoder"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "dpr",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "projection_dim": 0,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.41.0",
23
+ "type_vocab_size": 2,
24
+ "vocab_size": 30522
 
25
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f434b5c6bf0c88b521fef8d65127ee9d96b7faf44b0953ccb728dde21f70df65
3
- size 2061032996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23af4d38c069c9b57aff6ef8d307b021d20d8de9e3d17293951c56fe977c0563
3
+ size 435593312
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DPRContextEncoderTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff