unni12345 commited on
Commit
9ff36f2
1 Parent(s): 3e09364

tokenizer files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "Blip2ForConditionalGeneration"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "initializer_range": 0.02,
8
+ "model_type": "blip-2",
9
+ "num_query_tokens": 32,
10
+ "qformer_config": {
11
+ "_name_or_path": "",
12
+ "add_cross_attention": false,
13
+ "architectures": null,
14
+ "attention_probs_dropout_prob": 0.1,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": null,
18
+ "chunk_size_feed_forward": 0,
19
+ "classifier_dropout": null,
20
+ "cross_attention_frequency": 2,
21
+ "cross_attention_hidden_size": null,
22
+ "decoder_start_token_id": null,
23
+ "diversity_penalty": 0.0,
24
+ "do_sample": false,
25
+ "early_stopping": false,
26
+ "encoder_hidden_size": 1408,
27
+ "encoder_no_repeat_ngram_size": 0,
28
+ "eos_token_id": null,
29
+ "exponential_decay_length_penalty": null,
30
+ "finetuning_task": null,
31
+ "forced_bos_token_id": null,
32
+ "forced_eos_token_id": null,
33
+ "hidden_act": "gelu",
34
+ "hidden_dropout_prob": 0.1,
35
+ "hidden_size": 768,
36
+ "id2label": {
37
+ "0": "LABEL_0",
38
+ "1": "LABEL_1"
39
+ },
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 3072,
42
+ "is_decoder": false,
43
+ "is_encoder_decoder": false,
44
+ "label2id": {
45
+ "LABEL_0": 0,
46
+ "LABEL_1": 1
47
+ },
48
+ "layer_norm_eps": 1e-12,
49
+ "length_penalty": 1.0,
50
+ "max_length": 20,
51
+ "max_position_embeddings": 512,
52
+ "min_length": 0,
53
+ "model_type": "blip_2_qformer",
54
+ "no_repeat_ngram_size": 0,
55
+ "num_attention_heads": 12,
56
+ "num_beam_groups": 1,
57
+ "num_beams": 1,
58
+ "num_hidden_layers": 12,
59
+ "num_return_sequences": 1,
60
+ "output_attentions": false,
61
+ "output_hidden_states": false,
62
+ "output_scores": false,
63
+ "pad_token_id": 0,
64
+ "position_embedding_type": "absolute",
65
+ "prefix": null,
66
+ "problem_type": null,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "sep_token_id": null,
73
+ "suppress_tokens": null,
74
+ "task_specific_params": null,
75
+ "temperature": 1.0,
76
+ "tf_legacy_loss": false,
77
+ "tie_encoder_decoder": false,
78
+ "tie_word_embeddings": true,
79
+ "tokenizer_class": null,
80
+ "top_k": 50,
81
+ "top_p": 1.0,
82
+ "torch_dtype": null,
83
+ "torchscript": false,
84
+ "transformers_version": "4.30.2",
85
+ "typical_p": 1.0,
86
+ "use_bfloat16": false,
87
+ "vocab_size": 30522
88
+ },
89
+ "text_config": {
90
+ "_name_or_path": "",
91
+ "add_cross_attention": false,
92
+ "architectures": null,
93
+ "bad_words_ids": null,
94
+ "begin_suppress_tokens": null,
95
+ "bos_token_id": 1,
96
+ "chunk_size_feed_forward": 0,
97
+ "cross_attention_hidden_size": null,
98
+ "decoder_start_token_id": null,
99
+ "diversity_penalty": 0.0,
100
+ "do_sample": false,
101
+ "early_stopping": false,
102
+ "encoder_no_repeat_ngram_size": 0,
103
+ "eos_token_id": 2,
104
+ "exponential_decay_length_penalty": null,
105
+ "finetuning_task": null,
106
+ "forced_bos_token_id": null,
107
+ "forced_eos_token_id": null,
108
+ "hidden_act": "silu",
109
+ "hidden_size": 4096,
110
+ "id2label": {
111
+ "0": "LABEL_0",
112
+ "1": "LABEL_1"
113
+ },
114
+ "initializer_range": 0.02,
115
+ "intermediate_size": 11008,
116
+ "is_decoder": false,
117
+ "is_encoder_decoder": false,
118
+ "label2id": {
119
+ "LABEL_0": 0,
120
+ "LABEL_1": 1
121
+ },
122
+ "length_penalty": 1.0,
123
+ "max_length": 20,
124
+ "max_position_embeddings": 2048,
125
+ "min_length": 0,
126
+ "model_type": "llama",
127
+ "no_repeat_ngram_size": 0,
128
+ "num_attention_heads": 32,
129
+ "num_beam_groups": 1,
130
+ "num_beams": 1,
131
+ "num_hidden_layers": 32,
132
+ "num_return_sequences": 1,
133
+ "output_attentions": false,
134
+ "output_hidden_states": false,
135
+ "output_scores": false,
136
+ "pad_token_id": 0,
137
+ "prefix": null,
138
+ "problem_type": null,
139
+ "pruned_heads": {},
140
+ "remove_invalid_values": false,
141
+ "repetition_penalty": 1.0,
142
+ "return_dict": true,
143
+ "return_dict_in_generate": false,
144
+ "rms_norm_eps": 1e-06,
145
+ "sep_token_id": null,
146
+ "suppress_tokens": null,
147
+ "task_specific_params": null,
148
+ "temperature": 1.0,
149
+ "tf_legacy_loss": false,
150
+ "tie_encoder_decoder": false,
151
+ "tie_word_embeddings": false,
152
+ "tokenizer_class": null,
153
+ "top_k": 50,
154
+ "top_p": 1.0,
155
+ "torch_dtype": null,
156
+ "torchscript": false,
157
+ "transformers_version": "4.30.2",
158
+ "typical_p": 1.0,
159
+ "use_bfloat16": false,
160
+ "use_cache": true,
161
+ "vocab_size": 32000
162
+ },
163
+ "tie_word_embeddings": false,
164
+ "torch_dtype": "float32",
165
+ "transformers_version": null,
166
+ "use_decoder_only_language_model": true,
167
+ "vision_config": {
168
+ "_name_or_path": "",
169
+ "add_cross_attention": false,
170
+ "architectures": null,
171
+ "attention_dropout": 0.0,
172
+ "bad_words_ids": null,
173
+ "begin_suppress_tokens": null,
174
+ "bos_token_id": null,
175
+ "chunk_size_feed_forward": 0,
176
+ "cross_attention_hidden_size": null,
177
+ "decoder_start_token_id": null,
178
+ "diversity_penalty": 0.0,
179
+ "do_sample": false,
180
+ "dropout": 0.0,
181
+ "early_stopping": false,
182
+ "encoder_no_repeat_ngram_size": 0,
183
+ "eos_token_id": null,
184
+ "exponential_decay_length_penalty": null,
185
+ "finetuning_task": null,
186
+ "forced_bos_token_id": null,
187
+ "forced_eos_token_id": null,
188
+ "hidden_act": "gelu",
189
+ "hidden_size": 1408,
190
+ "id2label": {
191
+ "0": "LABEL_0",
192
+ "1": "LABEL_1"
193
+ },
194
+ "image_size": 224,
195
+ "initializer_factor": 1.0,
196
+ "initializer_range": 1e-10,
197
+ "intermediate_size": 6144,
198
+ "is_decoder": false,
199
+ "is_encoder_decoder": false,
200
+ "label2id": {
201
+ "LABEL_0": 0,
202
+ "LABEL_1": 1
203
+ },
204
+ "layer_norm_eps": 1e-05,
205
+ "length_penalty": 1.0,
206
+ "max_length": 20,
207
+ "min_length": 0,
208
+ "model_type": "blip_2_vision_model",
209
+ "no_repeat_ngram_size": 0,
210
+ "num_attention_heads": 16,
211
+ "num_beam_groups": 1,
212
+ "num_beams": 1,
213
+ "num_channels": 3,
214
+ "num_hidden_layers": 39,
215
+ "num_return_sequences": 1,
216
+ "output_attentions": false,
217
+ "output_hidden_states": false,
218
+ "output_scores": false,
219
+ "pad_token_id": null,
220
+ "patch_size": 14,
221
+ "prefix": null,
222
+ "problem_type": null,
223
+ "projection_dim": 512,
224
+ "pruned_heads": {},
225
+ "qkv_bias": true,
226
+ "remove_invalid_values": false,
227
+ "repetition_penalty": 1.0,
228
+ "return_dict": true,
229
+ "return_dict_in_generate": false,
230
+ "sep_token_id": null,
231
+ "suppress_tokens": null,
232
+ "task_specific_params": null,
233
+ "temperature": 1.0,
234
+ "tf_legacy_loss": false,
235
+ "tie_encoder_decoder": false,
236
+ "tie_word_embeddings": true,
237
+ "tokenizer_class": null,
238
+ "top_k": 50,
239
+ "top_p": 1.0,
240
+ "torch_dtype": null,
241
+ "torchscript": false,
242
+ "transformers_version": "4.30.2",
243
+ "typical_p": 1.0,
244
+ "use_bfloat16": false
245
+ }
246
+ }
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "[PAD]",
17
+ "unk_token": {
18
+ "content": "",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": null,
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }