LazerLambda
commited on
Commit
•
486b090
1
Parent(s):
1a38575
Upload 4 files
Browse files- MLW_Tokenizer.json +164 -0
- config.json +207 -0
- generation_config.json +13 -0
- 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
|