Harsh Trivedi
commited on
Commit
•
fd4d91b
1
Parent(s):
635ad37
update.
Browse files- added_tokens.json +68 -1
- config.json +5 -2
- pytorch_model.bin +2 -2
- special_tokens_map.json +17 -1
- tokenizer_config.json +114 -1
added_tokens.json
CHANGED
@@ -1 +1,68 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<ss>": 32146,
|
3 |
+
"[CHPD]": 32150,
|
4 |
+
"[CND]": 32147,
|
5 |
+
"[COLD]": 32140,
|
6 |
+
"[CTANS]": 32151,
|
7 |
+
"[CTCNINSINA]": 32155,
|
8 |
+
"[CTCNINTA]": 32154,
|
9 |
+
"[CTOUINSINA]": 32153,
|
10 |
+
"[CTOUINTA]": 32152,
|
11 |
+
"[DAY]": 32163,
|
12 |
+
"[DFB]": 32142,
|
13 |
+
"[DFD]": 32144,
|
14 |
+
"[DFE]": 32143,
|
15 |
+
"[MDFD]": 32145,
|
16 |
+
"[MONTH]": 32164,
|
17 |
+
"[ROWD]": 32141,
|
18 |
+
"[SCBN]": 32160,
|
19 |
+
"[SCBP]": 32159,
|
20 |
+
"[SCD]": 32158,
|
21 |
+
"[SCMN]": 32162,
|
22 |
+
"[SCMP]": 32161,
|
23 |
+
"[SIND]": 32149,
|
24 |
+
"[SNE]": 32157,
|
25 |
+
"[SNS]": 32156,
|
26 |
+
"[SOMD]": 32148,
|
27 |
+
"[YEAR]": 32165,
|
28 |
+
"are_items_different": 32103,
|
29 |
+
"are_items_same": 32102,
|
30 |
+
"arg_bool": 32131,
|
31 |
+
"arg_intersection": 32132,
|
32 |
+
"arg_maximum_date": 32116,
|
33 |
+
"arg_maximum_number": 32105,
|
34 |
+
"arg_minimum_date": 32115,
|
35 |
+
"arg_minimum_number": 32104,
|
36 |
+
"arithmetic_division": 32111,
|
37 |
+
"arithmetic_mean_single": 32108,
|
38 |
+
"arithmetic_multiplication": 32113,
|
39 |
+
"arithmetic_subtraction": 32112,
|
40 |
+
"arithmetic_sum_multiple": 32110,
|
41 |
+
"arithmetic_sum_single": 32109,
|
42 |
+
"boolean": 32101,
|
43 |
+
"compare_dates": 32120,
|
44 |
+
"compare_numbers": 32114,
|
45 |
+
"date_subtraction": 32119,
|
46 |
+
"filter_a_where_b_is_compared_to": 32128,
|
47 |
+
"filter_a_where_b_is_compared_to_date": 32124,
|
48 |
+
"filter_a_where_b_is_given_value": 32127,
|
49 |
+
"filter_a_where_b_is_max": 32125,
|
50 |
+
"filter_a_where_b_is_max_date": 32122,
|
51 |
+
"filter_a_where_b_is_min": 32126,
|
52 |
+
"filter_a_where_b_is_min_date": 32123,
|
53 |
+
"grouped_count": 32134,
|
54 |
+
"grouped_mean": 32135,
|
55 |
+
"grouped_sum": 32136,
|
56 |
+
"intersection": 32133,
|
57 |
+
"kth_highest": 32137,
|
58 |
+
"kth_lowest": 32138,
|
59 |
+
"list_subtraction": 32121,
|
60 |
+
"logical_and": 32130,
|
61 |
+
"logical_or": 32129,
|
62 |
+
"maximum_date": 32118,
|
63 |
+
"maximum_number": 32107,
|
64 |
+
"minimum_date": 32117,
|
65 |
+
"minimum_number": 32106,
|
66 |
+
"null": 32139,
|
67 |
+
"select": 32100
|
68 |
+
}
|
config.json
CHANGED
@@ -7,12 +7,13 @@
|
|
7 |
"d_kv": 64,
|
8 |
"d_model": 1024,
|
9 |
"decoder_start_token_id": 0,
|
|
|
10 |
"dropout_rate": 0.1,
|
11 |
"eos_token_id": 1,
|
12 |
"feed_forward_proj": "relu",
|
13 |
-
"gradient_checkpointing": false,
|
14 |
"initializer_factor": 1.0,
|
15 |
"is_encoder_decoder": true,
|
|
|
16 |
"layer_norm_epsilon": 1e-06,
|
17 |
"model_type": "t5",
|
18 |
"n_positions": 512,
|
@@ -21,6 +22,7 @@
|
|
21 |
"num_layers": 24,
|
22 |
"output_past": true,
|
23 |
"pad_token_id": 0,
|
|
|
24 |
"relative_attention_num_buckets": 32,
|
25 |
"task_specific_params": {
|
26 |
"summarization": {
|
@@ -51,8 +53,9 @@
|
|
51 |
"prefix": "translate English to Romanian: "
|
52 |
}
|
53 |
},
|
|
|
54 |
"torch_dtype": "float32",
|
55 |
-
"transformers_version": "4.
|
56 |
"use_cache": true,
|
57 |
"vocab_size": 32166
|
58 |
}
|
|
|
7 |
"d_kv": 64,
|
8 |
"d_model": 1024,
|
9 |
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "relu",
|
11 |
"dropout_rate": 0.1,
|
12 |
"eos_token_id": 1,
|
13 |
"feed_forward_proj": "relu",
|
|
|
14 |
"initializer_factor": 1.0,
|
15 |
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": false,
|
17 |
"layer_norm_epsilon": 1e-06,
|
18 |
"model_type": "t5",
|
19 |
"n_positions": 512,
|
|
|
22 |
"num_layers": 24,
|
23 |
"output_past": true,
|
24 |
"pad_token_id": 0,
|
25 |
+
"relative_attention_max_distance": 128,
|
26 |
"relative_attention_num_buckets": 32,
|
27 |
"task_specific_params": {
|
28 |
"summarization": {
|
|
|
53 |
"prefix": "translate English to Romanian: "
|
54 |
}
|
55 |
},
|
56 |
+
"tie_word_embeddings": false,
|
57 |
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.24.0",
|
59 |
"use_cache": true,
|
60 |
"vocab_size": 32166
|
61 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed2932e6709bce89a0c3cf3ff7ea1ef1a4e9513472ea79b2ade0b3ee62d75da9
|
3 |
+
size 3082745477
|
special_tokens_map.json
CHANGED
@@ -1 +1,17 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"0",
|
4 |
+
"1",
|
5 |
+
"2",
|
6 |
+
"3",
|
7 |
+
"4",
|
8 |
+
"5",
|
9 |
+
"6",
|
10 |
+
"7",
|
11 |
+
"8",
|
12 |
+
"9"
|
13 |
+
],
|
14 |
+
"eos_token": "</s>",
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"unk_token": "<unk>"
|
17 |
+
}
|
tokenizer_config.json
CHANGED
@@ -1 +1,114 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_special_tokens": false,
|
3 |
+
"additional_special_tokens": [
|
4 |
+
"<extra_id_0>",
|
5 |
+
"<extra_id_1>",
|
6 |
+
"<extra_id_2>",
|
7 |
+
"<extra_id_3>",
|
8 |
+
"<extra_id_4>",
|
9 |
+
"<extra_id_5>",
|
10 |
+
"<extra_id_6>",
|
11 |
+
"<extra_id_7>",
|
12 |
+
"<extra_id_8>",
|
13 |
+
"<extra_id_9>",
|
14 |
+
"<extra_id_10>",
|
15 |
+
"<extra_id_11>",
|
16 |
+
"<extra_id_12>",
|
17 |
+
"<extra_id_13>",
|
18 |
+
"<extra_id_14>",
|
19 |
+
"<extra_id_15>",
|
20 |
+
"<extra_id_16>",
|
21 |
+
"<extra_id_17>",
|
22 |
+
"<extra_id_18>",
|
23 |
+
"<extra_id_19>",
|
24 |
+
"<extra_id_20>",
|
25 |
+
"<extra_id_21>",
|
26 |
+
"<extra_id_22>",
|
27 |
+
"<extra_id_23>",
|
28 |
+
"<extra_id_24>",
|
29 |
+
"<extra_id_25>",
|
30 |
+
"<extra_id_26>",
|
31 |
+
"<extra_id_27>",
|
32 |
+
"<extra_id_28>",
|
33 |
+
"<extra_id_29>",
|
34 |
+
"<extra_id_30>",
|
35 |
+
"<extra_id_31>",
|
36 |
+
"<extra_id_32>",
|
37 |
+
"<extra_id_33>",
|
38 |
+
"<extra_id_34>",
|
39 |
+
"<extra_id_35>",
|
40 |
+
"<extra_id_36>",
|
41 |
+
"<extra_id_37>",
|
42 |
+
"<extra_id_38>",
|
43 |
+
"<extra_id_39>",
|
44 |
+
"<extra_id_40>",
|
45 |
+
"<extra_id_41>",
|
46 |
+
"<extra_id_42>",
|
47 |
+
"<extra_id_43>",
|
48 |
+
"<extra_id_44>",
|
49 |
+
"<extra_id_45>",
|
50 |
+
"<extra_id_46>",
|
51 |
+
"<extra_id_47>",
|
52 |
+
"<extra_id_48>",
|
53 |
+
"<extra_id_49>",
|
54 |
+
"<extra_id_50>",
|
55 |
+
"<extra_id_51>",
|
56 |
+
"<extra_id_52>",
|
57 |
+
"<extra_id_53>",
|
58 |
+
"<extra_id_54>",
|
59 |
+
"<extra_id_55>",
|
60 |
+
"<extra_id_56>",
|
61 |
+
"<extra_id_57>",
|
62 |
+
"<extra_id_58>",
|
63 |
+
"<extra_id_59>",
|
64 |
+
"<extra_id_60>",
|
65 |
+
"<extra_id_61>",
|
66 |
+
"<extra_id_62>",
|
67 |
+
"<extra_id_63>",
|
68 |
+
"<extra_id_64>",
|
69 |
+
"<extra_id_65>",
|
70 |
+
"<extra_id_66>",
|
71 |
+
"<extra_id_67>",
|
72 |
+
"<extra_id_68>",
|
73 |
+
"<extra_id_69>",
|
74 |
+
"<extra_id_70>",
|
75 |
+
"<extra_id_71>",
|
76 |
+
"<extra_id_72>",
|
77 |
+
"<extra_id_73>",
|
78 |
+
"<extra_id_74>",
|
79 |
+
"<extra_id_75>",
|
80 |
+
"<extra_id_76>",
|
81 |
+
"<extra_id_77>",
|
82 |
+
"<extra_id_78>",
|
83 |
+
"<extra_id_79>",
|
84 |
+
"<extra_id_80>",
|
85 |
+
"<extra_id_81>",
|
86 |
+
"<extra_id_82>",
|
87 |
+
"<extra_id_83>",
|
88 |
+
"<extra_id_84>",
|
89 |
+
"<extra_id_85>",
|
90 |
+
"<extra_id_86>",
|
91 |
+
"<extra_id_87>",
|
92 |
+
"<extra_id_88>",
|
93 |
+
"<extra_id_89>",
|
94 |
+
"<extra_id_90>",
|
95 |
+
"<extra_id_91>",
|
96 |
+
"<extra_id_92>",
|
97 |
+
"<extra_id_93>",
|
98 |
+
"<extra_id_94>",
|
99 |
+
"<extra_id_95>",
|
100 |
+
"<extra_id_96>",
|
101 |
+
"<extra_id_97>",
|
102 |
+
"<extra_id_98>",
|
103 |
+
"<extra_id_99>"
|
104 |
+
],
|
105 |
+
"eos_token": "</s>",
|
106 |
+
"extra_ids": 100,
|
107 |
+
"model_max_length": 512,
|
108 |
+
"name_or_path": "t5-large",
|
109 |
+
"pad_token": "<pad>",
|
110 |
+
"sp_model_kwargs": {},
|
111 |
+
"special_tokens_map_file": null,
|
112 |
+
"tokenizer_class": "T5Tokenizer",
|
113 |
+
"unk_token": "<unk>"
|
114 |
+
}
|