Upload 6 files
Browse files- added_tokens .json +102 -0
- config .json +61 -0
- generation_config json.json +7 -0
- model .safetensors +3 -0
- spiece .model +3 -0
- tokenizer_config .json +123 -0
added_tokens .json
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<extra_id_0>": 32099,
|
3 |
+
"<extra_id_10>": 32089,
|
4 |
+
"<extra_id_11>": 32088,
|
5 |
+
"<extra_id_12>": 32087,
|
6 |
+
"<extra_id_13>": 32086,
|
7 |
+
"<extra_id_14>": 32085,
|
8 |
+
"<extra_id_15>": 32084,
|
9 |
+
"<extra_id_16>": 32083,
|
10 |
+
"<extra_id_17>": 32082,
|
11 |
+
"<extra_id_18>": 32081,
|
12 |
+
"<extra_id_19>": 32080,
|
13 |
+
"<extra_id_1>": 32098,
|
14 |
+
"<extra_id_20>": 32079,
|
15 |
+
"<extra_id_21>": 32078,
|
16 |
+
"<extra_id_22>": 32077,
|
17 |
+
"<extra_id_23>": 32076,
|
18 |
+
"<extra_id_24>": 32075,
|
19 |
+
"<extra_id_25>": 32074,
|
20 |
+
"<extra_id_26>": 32073,
|
21 |
+
"<extra_id_27>": 32072,
|
22 |
+
"<extra_id_28>": 32071,
|
23 |
+
"<extra_id_29>": 32070,
|
24 |
+
"<extra_id_2>": 32097,
|
25 |
+
"<extra_id_30>": 32069,
|
26 |
+
"<extra_id_31>": 32068,
|
27 |
+
"<extra_id_32>": 32067,
|
28 |
+
"<extra_id_33>": 32066,
|
29 |
+
"<extra_id_34>": 32065,
|
30 |
+
"<extra_id_35>": 32064,
|
31 |
+
"<extra_id_36>": 32063,
|
32 |
+
"<extra_id_37>": 32062,
|
33 |
+
"<extra_id_38>": 32061,
|
34 |
+
"<extra_id_39>": 32060,
|
35 |
+
"<extra_id_3>": 32096,
|
36 |
+
"<extra_id_40>": 32059,
|
37 |
+
"<extra_id_41>": 32058,
|
38 |
+
"<extra_id_42>": 32057,
|
39 |
+
"<extra_id_43>": 32056,
|
40 |
+
"<extra_id_44>": 32055,
|
41 |
+
"<extra_id_45>": 32054,
|
42 |
+
"<extra_id_46>": 32053,
|
43 |
+
"<extra_id_47>": 32052,
|
44 |
+
"<extra_id_48>": 32051,
|
45 |
+
"<extra_id_49>": 32050,
|
46 |
+
"<extra_id_4>": 32095,
|
47 |
+
"<extra_id_50>": 32049,
|
48 |
+
"<extra_id_51>": 32048,
|
49 |
+
"<extra_id_52>": 32047,
|
50 |
+
"<extra_id_53>": 32046,
|
51 |
+
"<extra_id_54>": 32045,
|
52 |
+
"<extra_id_55>": 32044,
|
53 |
+
"<extra_id_56>": 32043,
|
54 |
+
"<extra_id_57>": 32042,
|
55 |
+
"<extra_id_58>": 32041,
|
56 |
+
"<extra_id_59>": 32040,
|
57 |
+
"<extra_id_5>": 32094,
|
58 |
+
"<extra_id_60>": 32039,
|
59 |
+
"<extra_id_61>": 32038,
|
60 |
+
"<extra_id_62>": 32037,
|
61 |
+
"<extra_id_63>": 32036,
|
62 |
+
"<extra_id_64>": 32035,
|
63 |
+
"<extra_id_65>": 32034,
|
64 |
+
"<extra_id_66>": 32033,
|
65 |
+
"<extra_id_67>": 32032,
|
66 |
+
"<extra_id_68>": 32031,
|
67 |
+
"<extra_id_69>": 32030,
|
68 |
+
"<extra_id_6>": 32093,
|
69 |
+
"<extra_id_70>": 32029,
|
70 |
+
"<extra_id_71>": 32028,
|
71 |
+
"<extra_id_72>": 32027,
|
72 |
+
"<extra_id_73>": 32026,
|
73 |
+
"<extra_id_74>": 32025,
|
74 |
+
"<extra_id_75>": 32024,
|
75 |
+
"<extra_id_76>": 32023,
|
76 |
+
"<extra_id_77>": 32022,
|
77 |
+
"<extra_id_78>": 32021,
|
78 |
+
"<extra_id_79>": 32020,
|
79 |
+
"<extra_id_7>": 32092,
|
80 |
+
"<extra_id_80>": 32019,
|
81 |
+
"<extra_id_81>": 32018,
|
82 |
+
"<extra_id_82>": 32017,
|
83 |
+
"<extra_id_83>": 32016,
|
84 |
+
"<extra_id_84>": 32015,
|
85 |
+
"<extra_id_85>": 32014,
|
86 |
+
"<extra_id_86>": 32013,
|
87 |
+
"<extra_id_87>": 32012,
|
88 |
+
"<extra_id_88>": 32011,
|
89 |
+
"<extra_id_89>": 32010,
|
90 |
+
"<extra_id_8>": 32091,
|
91 |
+
"<extra_id_90>": 32009,
|
92 |
+
"<extra_id_91>": 32008,
|
93 |
+
"<extra_id_92>": 32007,
|
94 |
+
"<extra_id_93>": 32006,
|
95 |
+
"<extra_id_94>": 32005,
|
96 |
+
"<extra_id_95>": 32004,
|
97 |
+
"<extra_id_96>": 32003,
|
98 |
+
"<extra_id_97>": 32002,
|
99 |
+
"<extra_id_98>": 32001,
|
100 |
+
"<extra_id_99>": 32000,
|
101 |
+
"<extra_id_9>": 32090
|
102 |
+
}
|
config .json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./medical_bert",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 3072,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "relu",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "relu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": false,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 12,
|
22 |
+
"num_heads": 12,
|
23 |
+
"num_layers": 12,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_max_distance": 128,
|
27 |
+
"relative_attention_num_buckets": 32,
|
28 |
+
"task_specific_params": {
|
29 |
+
"summarization": {
|
30 |
+
"early_stopping": true,
|
31 |
+
"length_penalty": 2.0,
|
32 |
+
"max_length": 200,
|
33 |
+
"min_length": 30,
|
34 |
+
"no_repeat_ngram_size": 3,
|
35 |
+
"num_beams": 4,
|
36 |
+
"prefix": "summarize: "
|
37 |
+
},
|
38 |
+
"translation_en_to_de": {
|
39 |
+
"early_stopping": true,
|
40 |
+
"max_length": 300,
|
41 |
+
"num_beams": 4,
|
42 |
+
"prefix": "translate English to German: "
|
43 |
+
},
|
44 |
+
"translation_en_to_fr": {
|
45 |
+
"early_stopping": true,
|
46 |
+
"max_length": 300,
|
47 |
+
"num_beams": 4,
|
48 |
+
"prefix": "translate English to French: "
|
49 |
+
},
|
50 |
+
"translation_en_to_ro": {
|
51 |
+
"early_stopping": true,
|
52 |
+
"max_length": 300,
|
53 |
+
"num_beams": 4,
|
54 |
+
"prefix": "translate English to Romanian: "
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"torch_dtype": "float16",
|
58 |
+
"transformers_version": "4.48.2",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 32128
|
61 |
+
}
|
generation_config json.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.48.2"
|
7 |
+
}
|
model .safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:075191fc4da5f4b868362b3d355d1892999fe2288098933d9fb59e07327cf806
|
3 |
+
size 445837528
|
spiece .model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
tokenizer_config .json
ADDED
@@ -0,0 +1,123 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "<unk>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "(",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
+
"content": ")",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"7": {
|
60 |
+
"content": "\"",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"8": {
|
68 |
+
"content": "-",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"9": {
|
76 |
+
"content": ".",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"10": {
|
84 |
+
"content": "–",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"11": {
|
92 |
+
"content": "£",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"12": {
|
100 |
+
"content": "€",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
}
|
107 |
+
},
|
108 |
+
"bos_token": "[CLS]",
|
109 |
+
"clean_up_tokenization_spaces": false,
|
110 |
+
"cls_token": "[CLS]",
|
111 |
+
"do_lower_case": true,
|
112 |
+
"eos_token": "[SEP]",
|
113 |
+
"extra_special_tokens": {},
|
114 |
+
"keep_accents": false,
|
115 |
+
"mask_token": "[MASK]",
|
116 |
+
"model_max_length": 512,
|
117 |
+
"pad_token": "<pad>",
|
118 |
+
"remove_space": true,
|
119 |
+
"sep_token": "[SEP]",
|
120 |
+
"sp_model_kwargs": {},
|
121 |
+
"tokenizer_class": "AlbertTokenizer",
|
122 |
+
"unk_token": "<unk>"
|
123 |
+
}
|