bert-crf

app.py

@@ -9,9 +9,9 @@ import json
 
 st.set_page_config(layout="wide")
 
-model = AutoModelForTokenClassification.from_pretrained("models/lusa", use_safetensors=True)
+model = AutoModelForTokenClassification.from_pretrained("./models/bert_crf", use_safetensors=True)
 
-tokenizer = AutoTokenizer.from_pretrained("models/lusa", model_max_length=512)
+tokenizer = AutoTokenizer.from_pretrained("./models/bert_crf", model_max_length=512)
 tagger = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy='first') #aggregation_strategy='max'
   
 

models/bert_crf/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "neuralmind/bert-base-portuguese-cased",
+  "architectures": [
+    "BertCRF"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "I-Time",
+    "1": "B-Time",
+    "2": "I-Event",
+    "3": "B-Spatial_Relation",
+    "4": "B-Participant",
+    "5": "O",
+    "6": "B-Event",
+    "7": "I-Spatial_Relation",
+    "8": "I-Participant"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Event": 6,
+    "B-Participant": 4,
+    "B-Spatial_Relation": 3,
+    "B-Time": 1,
+    "I-Event": 2,
+    "I-Participant": 8,
+    "I-Spatial_Relation": 7,
+    "I-Time": 0,
+    "O": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29794
+}

models/bert_crf/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d13498d68c4c240054dbcfa9755a89c5887a0e7cc623eaaec7bd33c6a6d6101
+size 433381856

models/bert_crf/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

models/bert_crf/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

models/bert_crf/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d9387a08c40ab2221a567520f6f2ab33976a32ed8307ecfa0f1aa4a5df67200
+size 5112