Upload 9 files
Browse files- .gitattributes +0 -1
- added_tokens.json +28 -0
- config.json +195 -0
- generation_config.json +10 -0
- preprocessor_config.json +26 -0
- special_tokens_map.json +8 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
@@ -25,7 +25,6 @@
|
|
25 |
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
*.wasm filter=lfs diff=lfs merge=lfs -text
|
|
|
25 |
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
|
|
28 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
29 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
30 |
*.wasm filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 32000,
|
3 |
+
"<s_cord-v2>": 32025,
|
4 |
+
"কুষ্টিয়া": 32001,
|
5 |
+
"খূলণা": 32022,
|
6 |
+
"চট্টমেটড়ো": 32006,
|
7 |
+
"চট্টো": 32007,
|
8 |
+
"চট্রো": 32016,
|
9 |
+
"চুয়াডাঙ্গা": 32019,
|
10 |
+
"জশর": 32023,
|
11 |
+
"জোশোড়": 32004,
|
12 |
+
"জোষোড়": 32010,
|
13 |
+
"ঝিনাইদাহ": 32020,
|
14 |
+
"টাংগাইল": 32005,
|
15 |
+
"টাঞাঈল": 32012,
|
16 |
+
"ঢাককা": 32024,
|
17 |
+
"ধাকা": 32011,
|
18 |
+
"নারায়ণগঞ্জ": 32003,
|
19 |
+
"নারায়নগঞ্জ": 32008,
|
20 |
+
"নোয়াখালী": 32021,
|
21 |
+
"নড়াইল": 32009,
|
22 |
+
"বগুড়া": 32017,
|
23 |
+
"মেটড়ো": 32015,
|
24 |
+
"ময়মনসিংহ": 32002,
|
25 |
+
"যশোর": 32018,
|
26 |
+
"রাজবাড়ী": 32013,
|
27 |
+
"্ডহাকা": 32014
|
28 |
+
}
|
config.json
ADDED
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": "8c665dab03c49568dff0773ded60bc45918a16d2",
|
3 |
+
"_name_or_path": "sakib131/donut-bn-LP",
|
4 |
+
"architectures": [
|
5 |
+
"VisionEncoderDecoderModel"
|
6 |
+
],
|
7 |
+
"decoder": {
|
8 |
+
"_name_or_path": "",
|
9 |
+
"activation_dropout": 0.0,
|
10 |
+
"activation_function": "gelu",
|
11 |
+
"add_cross_attention": true,
|
12 |
+
"add_final_layer_norm": true,
|
13 |
+
"architectures": null,
|
14 |
+
"attention_dropout": 0.0,
|
15 |
+
"bad_words_ids": null,
|
16 |
+
"begin_suppress_tokens": null,
|
17 |
+
"bos_token_id": 0,
|
18 |
+
"chunk_size_feed_forward": 0,
|
19 |
+
"classifier_dropout": 0.0,
|
20 |
+
"cross_attention_hidden_size": null,
|
21 |
+
"d_model": 1024,
|
22 |
+
"decoder_attention_heads": 16,
|
23 |
+
"decoder_ffn_dim": 4096,
|
24 |
+
"decoder_layerdrop": 0.0,
|
25 |
+
"decoder_layers": 4,
|
26 |
+
"decoder_start_token_id": null,
|
27 |
+
"diversity_penalty": 0.0,
|
28 |
+
"do_sample": false,
|
29 |
+
"dropout": 0.1,
|
30 |
+
"early_stopping": false,
|
31 |
+
"encoder_attention_heads": 16,
|
32 |
+
"encoder_ffn_dim": 4096,
|
33 |
+
"encoder_layerdrop": 0.0,
|
34 |
+
"encoder_layers": 12,
|
35 |
+
"encoder_no_repeat_ngram_size": 0,
|
36 |
+
"eos_token_id": 2,
|
37 |
+
"exponential_decay_length_penalty": null,
|
38 |
+
"finetuning_task": null,
|
39 |
+
"forced_bos_token_id": null,
|
40 |
+
"forced_eos_token_id": 2,
|
41 |
+
"id2label": {
|
42 |
+
"0": "LABEL_0",
|
43 |
+
"1": "LABEL_1"
|
44 |
+
},
|
45 |
+
"init_std": 0.02,
|
46 |
+
"is_decoder": true,
|
47 |
+
"is_encoder_decoder": false,
|
48 |
+
"label2id": {
|
49 |
+
"LABEL_0": 0,
|
50 |
+
"LABEL_1": 1
|
51 |
+
},
|
52 |
+
"length_penalty": 1.0,
|
53 |
+
"max_length": 100,
|
54 |
+
"max_position_embeddings": 1536,
|
55 |
+
"min_length": 0,
|
56 |
+
"model_type": "mbart",
|
57 |
+
"no_repeat_ngram_size": 0,
|
58 |
+
"num_beam_groups": 1,
|
59 |
+
"num_beams": 1,
|
60 |
+
"num_hidden_layers": 12,
|
61 |
+
"num_return_sequences": 1,
|
62 |
+
"output_attentions": false,
|
63 |
+
"output_hidden_states": false,
|
64 |
+
"output_scores": false,
|
65 |
+
"pad_token_id": 1,
|
66 |
+
"prefix": null,
|
67 |
+
"problem_type": null,
|
68 |
+
"pruned_heads": {},
|
69 |
+
"remove_invalid_values": false,
|
70 |
+
"repetition_penalty": 1.0,
|
71 |
+
"return_dict": true,
|
72 |
+
"return_dict_in_generate": false,
|
73 |
+
"scale_embedding": true,
|
74 |
+
"sep_token_id": null,
|
75 |
+
"suppress_tokens": null,
|
76 |
+
"task_specific_params": null,
|
77 |
+
"temperature": 1.0,
|
78 |
+
"tf_legacy_loss": false,
|
79 |
+
"tie_encoder_decoder": false,
|
80 |
+
"tie_word_embeddings": true,
|
81 |
+
"tokenizer_class": null,
|
82 |
+
"top_k": 50,
|
83 |
+
"top_p": 1.0,
|
84 |
+
"torch_dtype": null,
|
85 |
+
"torchscript": false,
|
86 |
+
"transformers_version": "4.29.2",
|
87 |
+
"typical_p": 1.0,
|
88 |
+
"use_bfloat16": false,
|
89 |
+
"use_cache": true,
|
90 |
+
"vocab_size": 32026
|
91 |
+
},
|
92 |
+
"decoder_start_token_id": 32025,
|
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 |
+
14,
|
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": 128,
|
115 |
+
"encoder_no_repeat_ngram_size": 0,
|
116 |
+
"eos_token_id": null,
|
117 |
+
"exponential_decay_length_penalty": null,
|
118 |
+
"finetuning_task": null,
|
119 |
+
"forced_bos_token_id": null,
|
120 |
+
"forced_eos_token_id": null,
|
121 |
+
"hidden_act": "gelu",
|
122 |
+
"hidden_dropout_prob": 0.0,
|
123 |
+
"hidden_size": 1024,
|
124 |
+
"id2label": {
|
125 |
+
"0": "LABEL_0",
|
126 |
+
"1": "LABEL_1"
|
127 |
+
},
|
128 |
+
"image_size": [
|
129 |
+
320,
|
130 |
+
640
|
131 |
+
],
|
132 |
+
"initializer_range": 0.02,
|
133 |
+
"is_decoder": false,
|
134 |
+
"is_encoder_decoder": false,
|
135 |
+
"label2id": {
|
136 |
+
"LABEL_0": 0,
|
137 |
+
"LABEL_1": 1
|
138 |
+
},
|
139 |
+
"layer_norm_eps": 1e-05,
|
140 |
+
"length_penalty": 1.0,
|
141 |
+
"max_length": 20,
|
142 |
+
"min_length": 0,
|
143 |
+
"mlp_ratio": 4.0,
|
144 |
+
"model_type": "donut-swin",
|
145 |
+
"no_repeat_ngram_size": 0,
|
146 |
+
"num_beam_groups": 1,
|
147 |
+
"num_beams": 1,
|
148 |
+
"num_channels": 3,
|
149 |
+
"num_heads": [
|
150 |
+
4,
|
151 |
+
8,
|
152 |
+
16,
|
153 |
+
32
|
154 |
+
],
|
155 |
+
"num_layers": 4,
|
156 |
+
"num_return_sequences": 1,
|
157 |
+
"output_attentions": false,
|
158 |
+
"output_hidden_states": false,
|
159 |
+
"output_scores": false,
|
160 |
+
"pad_token_id": null,
|
161 |
+
"patch_size": 4,
|
162 |
+
"path_norm": true,
|
163 |
+
"prefix": null,
|
164 |
+
"problem_type": null,
|
165 |
+
"pruned_heads": {},
|
166 |
+
"qkv_bias": true,
|
167 |
+
"remove_invalid_values": false,
|
168 |
+
"repetition_penalty": 1.0,
|
169 |
+
"return_dict": true,
|
170 |
+
"return_dict_in_generate": false,
|
171 |
+
"sep_token_id": null,
|
172 |
+
"suppress_tokens": null,
|
173 |
+
"task_specific_params": null,
|
174 |
+
"temperature": 1.0,
|
175 |
+
"tf_legacy_loss": false,
|
176 |
+
"tie_encoder_decoder": false,
|
177 |
+
"tie_word_embeddings": true,
|
178 |
+
"tokenizer_class": null,
|
179 |
+
"top_k": 50,
|
180 |
+
"top_p": 1.0,
|
181 |
+
"torch_dtype": null,
|
182 |
+
"torchscript": false,
|
183 |
+
"transformers_version": "4.29.2",
|
184 |
+
"typical_p": 1.0,
|
185 |
+
"use_absolute_embeddings": false,
|
186 |
+
"use_bfloat16": false,
|
187 |
+
"window_size": 10
|
188 |
+
},
|
189 |
+
"is_encoder_decoder": true,
|
190 |
+
"model_type": "vision-encoder-decoder",
|
191 |
+
"pad_token_id": 0,
|
192 |
+
"tie_word_embeddings": false,
|
193 |
+
"torch_dtype": "float32",
|
194 |
+
"transformers_version": null
|
195 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 32025,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"forced_eos_token_id": 2,
|
7 |
+
"max_length": 100,
|
8 |
+
"pad_token_id": 0,
|
9 |
+
"transformers_version": "4.29.2"
|
10 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_align_long_axis": false,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_pad": true,
|
5 |
+
"do_rescale": true,
|
6 |
+
"do_resize": true,
|
7 |
+
"do_thumbnail": true,
|
8 |
+
"image_mean": [
|
9 |
+
0.5,
|
10 |
+
0.5,
|
11 |
+
0.5
|
12 |
+
],
|
13 |
+
"image_processor_type": "DonutImageProcessor",
|
14 |
+
"image_std": [
|
15 |
+
0.5,
|
16 |
+
0.5,
|
17 |
+
0.5
|
18 |
+
],
|
19 |
+
"processor_class": "DonutProcessor",
|
20 |
+
"resample": 2,
|
21 |
+
"rescale_factor": 0.00392156862745098,
|
22 |
+
"size": [
|
23 |
+
640,
|
24 |
+
320
|
25 |
+
]
|
26 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"pad_token": "[PAD]",
|
6 |
+
"sep_token": "[SEP]",
|
7 |
+
"unk_token": "[UNK]"
|
8 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"full_tokenizer_file": null,
|
7 |
+
"mask_token": "[MASK]",
|
8 |
+
"model_max_length": 1000000000000000019884624838656,
|
9 |
+
"never_split": null,
|
10 |
+
"pad_token": "[PAD]",
|
11 |
+
"processor_class": "DonutProcessor",
|
12 |
+
"sep_token": "[SEP]",
|
13 |
+
"strip_accents": null,
|
14 |
+
"tokenize_chinese_chars": false,
|
15 |
+
"tokenizer_class": "ElectraTokenizer",
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|