LazerLambda commited on
Commit
486b090
1 Parent(s): 1a38575

Upload 4 files

Browse files
Files changed (4) hide show
  1. MLW_Tokenizer.json +164 -0
  2. config.json +207 -0
  3. generation_config.json +13 -0
  4. pytorch_model.bin +3 -0
MLW_Tokenizer.json ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "[BOS]",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "[UNK]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "[EOS]",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": null,
35
+ "pre_tokenizer": null,
36
+ "post_processor": {
37
+ "type": "TemplateProcessing",
38
+ "single": [
39
+ {
40
+ "Sequence": {
41
+ "id": "A",
42
+ "type_id": 0
43
+ }
44
+ },
45
+ {
46
+ "SpecialToken": {
47
+ "id": "[EOS]",
48
+ "type_id": 0
49
+ }
50
+ }
51
+ ],
52
+ "pair": [
53
+ {
54
+ "Sequence": {
55
+ "id": "A",
56
+ "type_id": 0
57
+ }
58
+ },
59
+ {
60
+ "Sequence": {
61
+ "id": "B",
62
+ "type_id": 1
63
+ }
64
+ }
65
+ ],
66
+ "special_tokens": {
67
+ "[EOS]": {
68
+ "id": "[EOS]",
69
+ "ids": [
70
+ 2
71
+ ],
72
+ "tokens": [
73
+ "[EOS]"
74
+ ]
75
+ }
76
+ }
77
+ },
78
+ "decoder": {
79
+ "type": "ByteLevel",
80
+ "add_prefix_space": true,
81
+ "trim_offsets": true,
82
+ "use_regex": true
83
+ },
84
+ "model": {
85
+ "type": "BPE",
86
+ "dropout": null,
87
+ "unk_token": "[UNK]",
88
+ "continuing_subword_prefix": null,
89
+ "end_of_word_suffix": null,
90
+ "fuse_unk": false,
91
+ "vocab": {
92
+ "[BOS]": 0,
93
+ "[UNK]": 1,
94
+ "[EOS]": 2,
95
+ " ": 3,
96
+ "#": 4,
97
+ "*": 5,
98
+ "-": 6,
99
+ ".": 7,
100
+ ">": 8,
101
+ "A": 9,
102
+ "B": 10,
103
+ "C": 11,
104
+ "E": 12,
105
+ "L": 13,
106
+ "M": 14,
107
+ "N": 15,
108
+ "O": 16,
109
+ "P": 17,
110
+ "Q": 18,
111
+ "R": 19,
112
+ "S": 20,
113
+ "T": 21,
114
+ "U": 22,
115
+ "V": 23,
116
+ "W": 24,
117
+ "Z": 25,
118
+ "`": 26,
119
+ "a": 27,
120
+ "b": 28,
121
+ "c": 29,
122
+ "d": 30,
123
+ "e": 31,
124
+ "f": 32,
125
+ "g": 33,
126
+ "h": 34,
127
+ "i": 35,
128
+ "j": 36,
129
+ "k": 37,
130
+ "l": 38,
131
+ "m": 39,
132
+ "n": 40,
133
+ "o": 41,
134
+ "p": 42,
135
+ "q": 43,
136
+ "r": 44,
137
+ "s": 45,
138
+ "t": 46,
139
+ "u": 47,
140
+ "v": 48,
141
+ "w": 49,
142
+ "x": 50,
143
+ "y": 51,
144
+ "z": 52,
145
+ "|": 53,
146
+ "us": 54,
147
+ "ti": 55,
148
+ "ri": 56,
149
+ "um": 57,
150
+ "co": 58,
151
+ "ra": 59,
152
+ "li": 60
153
+ },
154
+ "merges": [
155
+ "u s",
156
+ "t i",
157
+ "r i",
158
+ "u m",
159
+ "c o",
160
+ "r a",
161
+ "l i"
162
+ ]
163
+ }
164
+ }
config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "",
8
+ "activation_function": "gelu_new",
9
+ "add_cross_attention": true,
10
+ "architectures": null,
11
+ "attn_pdrop": 0.1,
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": 50256,
15
+ "chunk_size_feed_forward": 0,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "embd_pdrop": 0.1,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": 50256,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "is_decoder": true,
34
+ "is_encoder_decoder": false,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1
38
+ },
39
+ "layer_norm_epsilon": 1e-05,
40
+ "length_penalty": 1.0,
41
+ "max_length": 20,
42
+ "min_length": 0,
43
+ "model_type": "gpt2",
44
+ "n_embd": 768,
45
+ "n_head": 12,
46
+ "n_inner": null,
47
+ "n_layer": 12,
48
+ "n_positions": 1024,
49
+ "no_repeat_ngram_size": 0,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": null,
57
+ "prefix": null,
58
+ "problem_type": null,
59
+ "pruned_heads": {},
60
+ "remove_invalid_values": false,
61
+ "reorder_and_upcast_attn": false,
62
+ "repetition_penalty": 1.0,
63
+ "resid_pdrop": 0.1,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "scale_attn_by_inverse_layer_idx": false,
67
+ "scale_attn_weights": true,
68
+ "sep_token_id": null,
69
+ "summary_activation": null,
70
+ "summary_first_dropout": 0.1,
71
+ "summary_proj_to_labels": true,
72
+ "summary_type": "cls_index",
73
+ "summary_use_proj": true,
74
+ "suppress_tokens": null,
75
+ "task_specific_params": null,
76
+ "temperature": 1.0,
77
+ "tf_legacy_loss": false,
78
+ "tie_encoder_decoder": false,
79
+ "tie_word_embeddings": true,
80
+ "tokenizer_class": null,
81
+ "top_k": 50,
82
+ "top_p": 1.0,
83
+ "torch_dtype": null,
84
+ "torchscript": false,
85
+ "transformers_version": "4.26.1",
86
+ "typical_p": 1.0,
87
+ "use_bfloat16": false,
88
+ "use_cache": true,
89
+ "vocab_size": 62
90
+ },
91
+ "decoder_start_token_id": 0,
92
+ "early_stopping": true,
93
+ "encoder": {
94
+ "_name_or_path": "",
95
+ "add_cross_attention": false,
96
+ "architectures": null,
97
+ "attention_probs_dropout_prob": 0.0,
98
+ "bad_words_ids": null,
99
+ "begin_suppress_tokens": null,
100
+ "bos_token_id": null,
101
+ "chunk_size_feed_forward": 0,
102
+ "cross_attention_hidden_size": null,
103
+ "decoder_start_token_id": null,
104
+ "depths": [
105
+ 2,
106
+ 2,
107
+ 6,
108
+ 2
109
+ ],
110
+ "diversity_penalty": 0.0,
111
+ "do_sample": false,
112
+ "drop_path_rate": 0.1,
113
+ "early_stopping": false,
114
+ "embed_dim": 96,
115
+ "encoder_no_repeat_ngram_size": 0,
116
+ "encoder_stride": 32,
117
+ "eos_token_id": null,
118
+ "exponential_decay_length_penalty": null,
119
+ "finetuning_task": null,
120
+ "forced_bos_token_id": null,
121
+ "forced_eos_token_id": null,
122
+ "hidden_act": "gelu",
123
+ "hidden_dropout_prob": 0.0,
124
+ "hidden_size": 768,
125
+ "id2label": {
126
+ "0": "LABEL_0",
127
+ "1": "LABEL_1"
128
+ },
129
+ "image_size": 224,
130
+ "initializer_range": 0.02,
131
+ "is_decoder": false,
132
+ "is_encoder_decoder": false,
133
+ "label2id": {
134
+ "LABEL_0": 0,
135
+ "LABEL_1": 1
136
+ },
137
+ "layer_norm_eps": 1e-05,
138
+ "length_penalty": 1.0,
139
+ "max_length": 20,
140
+ "min_length": 0,
141
+ "mlp_ratio": 4.0,
142
+ "model_type": "swin",
143
+ "no_repeat_ngram_size": 0,
144
+ "num_beam_groups": 1,
145
+ "num_beams": 1,
146
+ "num_channels": 3,
147
+ "num_heads": [
148
+ 3,
149
+ 6,
150
+ 12,
151
+ 24
152
+ ],
153
+ "num_layers": 4,
154
+ "num_return_sequences": 1,
155
+ "out_features": null,
156
+ "output_attentions": false,
157
+ "output_hidden_states": false,
158
+ "output_scores": false,
159
+ "pad_token_id": null,
160
+ "patch_size": 4,
161
+ "path_norm": true,
162
+ "prefix": null,
163
+ "problem_type": null,
164
+ "pruned_heads": {},
165
+ "qkv_bias": true,
166
+ "remove_invalid_values": false,
167
+ "repetition_penalty": 1.0,
168
+ "return_dict": true,
169
+ "return_dict_in_generate": false,
170
+ "sep_token_id": null,
171
+ "stage_names": [
172
+ "stem",
173
+ "stage1",
174
+ "stage2",
175
+ "stage3",
176
+ "stage4"
177
+ ],
178
+ "suppress_tokens": null,
179
+ "task_specific_params": null,
180
+ "temperature": 1.0,
181
+ "tf_legacy_loss": false,
182
+ "tie_encoder_decoder": false,
183
+ "tie_word_embeddings": true,
184
+ "tokenizer_class": null,
185
+ "top_k": 50,
186
+ "top_p": 1.0,
187
+ "torch_dtype": null,
188
+ "torchscript": false,
189
+ "transformers_version": "4.26.1",
190
+ "typical_p": 1.0,
191
+ "use_absolute_embeddings": false,
192
+ "use_bfloat16": false,
193
+ "window_size": 7
194
+ },
195
+ "eos_token_id": 2,
196
+ "is_encoder_decoder": true,
197
+ "length_penalty": 2.0,
198
+ "max_length": 32,
199
+ "model_type": "vision-encoder-decoder",
200
+ "no_repeat_ngram_size": 3,
201
+ "num_beams": 4,
202
+ "pad_token_id": 61,
203
+ "tie_word_embeddings": false,
204
+ "torch_dtype": "float32",
205
+ "transformers_version": null,
206
+ "vocab_size": 62
207
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "decoder_start_token_id": 0,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "length_penalty": 2.0,
8
+ "max_length": 32,
9
+ "no_repeat_ngram_size": 3,
10
+ "num_beams": 4,
11
+ "pad_token_id": 61,
12
+ "transformers_version": "4.26.1"
13
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ef55c5c6e464b725620357bb04c9ccafed2c10a9272b5eedb5b19459b949ae
3
+ size 592681465