Spaces:
Build error
Build error
lusar_ner model
Browse files- models/lusa/config.json +19 -7
- models/lusa/model.safetensors +3 -0
- models/lusa/special_tokens_map.json +7 -1
- models/lusa/tokenizer_config.json +57 -1
- models/lusa/training_args.bin +2 -2
- models/lusa_old/config.json +42 -0
- models/{lusa → lusa_old}/pytorch_model.bin +0 -0
- models/lusa_old/special_tokens_map.json +1 -0
- models/lusa_old/tokenizer.json +0 -0
- models/lusa_old/tokenizer_config.json +1 -0
- models/lusa_old/training_args.bin +3 -0
- models/lusa_old/vocab.txt +0 -0
- models/lusa_old2/config.json +42 -0
- models/lusa_old2/model.safetensors +3 -0
- models/lusa_old2/special_tokens_map.json +7 -0
- models/lusa_old2/tokenizer.json +0 -0
- models/lusa_old2/tokenizer_config.json +57 -0
- models/lusa_old2/training_args.bin +3 -0
- models/lusa_old2/vocab.txt +0 -0
models/lusa/config.json
CHANGED
|
@@ -10,16 +10,28 @@
|
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
| 12 |
"id2label": {
|
| 13 |
-
"0": "I-
|
| 14 |
-
"1": "B-
|
| 15 |
-
"2": "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
},
|
| 17 |
"initializer_range": 0.02,
|
| 18 |
"intermediate_size": 3072,
|
| 19 |
"label2id": {
|
| 20 |
-
"B-Event":
|
| 21 |
-
"
|
| 22 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
},
|
| 24 |
"layer_norm_eps": 1e-12,
|
| 25 |
"max_position_embeddings": 512,
|
|
@@ -35,7 +47,7 @@
|
|
| 35 |
"pooler_type": "first_token_transform",
|
| 36 |
"position_embedding_type": "absolute",
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
-
"transformers_version": "4.
|
| 39 |
"type_vocab_size": 2,
|
| 40 |
"use_cache": true,
|
| 41 |
"vocab_size": 29794
|
|
|
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
| 12 |
"id2label": {
|
| 13 |
+
"0": "I-Time",
|
| 14 |
+
"1": "B-Spatial_Relation",
|
| 15 |
+
"2": "B-Participant",
|
| 16 |
+
"3": "I-Spatial_Relation",
|
| 17 |
+
"4": "I-Event",
|
| 18 |
+
"5": "O",
|
| 19 |
+
"6": "B-Event",
|
| 20 |
+
"7": "I-Participant",
|
| 21 |
+
"8": "B-Time"
|
| 22 |
},
|
| 23 |
"initializer_range": 0.02,
|
| 24 |
"intermediate_size": 3072,
|
| 25 |
"label2id": {
|
| 26 |
+
"B-Event": 6,
|
| 27 |
+
"B-Participant": 2,
|
| 28 |
+
"B-Spatial_Relation": 1,
|
| 29 |
+
"B-Time": 8,
|
| 30 |
+
"I-Event": 4,
|
| 31 |
+
"I-Participant": 7,
|
| 32 |
+
"I-Spatial_Relation": 3,
|
| 33 |
+
"I-Time": 0,
|
| 34 |
+
"O": 5
|
| 35 |
},
|
| 36 |
"layer_norm_eps": 1e-12,
|
| 37 |
"max_position_embeddings": 512,
|
|
|
|
| 47 |
"pooler_type": "first_token_transform",
|
| 48 |
"position_embedding_type": "absolute",
|
| 49 |
"torch_dtype": "float32",
|
| 50 |
+
"transformers_version": "4.41.0",
|
| 51 |
"type_vocab_size": 2,
|
| 52 |
"use_cache": true,
|
| 53 |
"vocab_size": 29794
|
models/lusa/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42835c1294dc265a4a0b5d88af0a519a8a9dd9aff2f92b47e596ec2a52131517
|
| 3 |
+
size 433381196
|
models/lusa/special_tokens_map.json
CHANGED
|
@@ -1 +1,7 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
models/lusa/tokenizer_config.json
CHANGED
|
@@ -1 +1,57 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
models/lusa/training_args.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 sha256:4d9387a08c40ab2221a567520f6f2ab33976a32ed8307ecfa0f1aa4a5df67200
|
| 3 |
+
size 5112
|
models/lusa_old/config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "neuralmind/bert-base-portuguese-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "I-Event",
|
| 14 |
+
"1": "B-Event",
|
| 15 |
+
"2": "O"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"B-Event": 1,
|
| 21 |
+
"I-Event": 0,
|
| 22 |
+
"O": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"output_past": true,
|
| 30 |
+
"pad_token_id": 0,
|
| 31 |
+
"pooler_fc_size": 768,
|
| 32 |
+
"pooler_num_attention_heads": 12,
|
| 33 |
+
"pooler_num_fc_layers": 3,
|
| 34 |
+
"pooler_size_per_head": 128,
|
| 35 |
+
"pooler_type": "first_token_transform",
|
| 36 |
+
"position_embedding_type": "absolute",
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.18.0",
|
| 39 |
+
"type_vocab_size": 2,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 29794
|
| 42 |
+
}
|
models/{lusa → lusa_old}/pytorch_model.bin
RENAMED
|
File without changes
|
models/lusa_old/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
models/lusa_old/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models/lusa_old/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/home/dock/.cache/huggingface/transformers/eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "neuralmind/bert-base-portuguese-cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
models/lusa_old/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72ae981987da18cf3cbbd058377b693d1e5b1d57242a27551b56f605e5bb3d11
|
| 3 |
+
size 3512
|
models/lusa_old/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models/lusa_old2/config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "neuralmind/bert-base-portuguese-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "B-Event",
|
| 14 |
+
"1": "O",
|
| 15 |
+
"2": "I-Event"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"B-Event": 0,
|
| 21 |
+
"I-Event": 2,
|
| 22 |
+
"O": 1
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"output_past": true,
|
| 30 |
+
"pad_token_id": 0,
|
| 31 |
+
"pooler_fc_size": 768,
|
| 32 |
+
"pooler_num_attention_heads": 12,
|
| 33 |
+
"pooler_num_fc_layers": 3,
|
| 34 |
+
"pooler_size_per_head": 128,
|
| 35 |
+
"pooler_type": "first_token_transform",
|
| 36 |
+
"position_embedding_type": "absolute",
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.41.0",
|
| 39 |
+
"type_vocab_size": 2,
|
| 40 |
+
"use_cache": true,
|
| 41 |
+
"vocab_size": 29794
|
| 42 |
+
}
|
models/lusa_old2/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f89f433e07b78678ee86593d3c7ae7073afb17f098deed25a017e7bca8b7ee7c
|
| 3 |
+
size 433362740
|
models/lusa_old2/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
models/lusa_old2/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
models/lusa_old2/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
models/lusa_old2/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78121e8ad5407d6265ddf7b5e06e8d933b95b92b7a4ccf18601ce7eaf17b12fa
|
| 3 |
+
size 5112
|
models/lusa_old2/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|