init project

README.md

@@ -0,0 +1,46 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: ner-vietnamese-electra-base
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# cv-ner
+
+This model is a fine-tuned version of [/datahdd/nhanv/git/nlp_toolkit/outputs/cv-ner](https://huggingface.co//datahdd/nhanv/git/nlp_toolkit/outputs/cv-ner) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+
+### Framework versions
+
+- Transformers 4.20.1
+- Pytorch 1.8.0+cu111
+- Datasets 2.4.0
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "NlpHUST/electra-base-vn",
+  "architectures": [
+    "ElectraForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-LOCATION",
+    "1": "B-MISCELLANEOUS",
+    "2": "B-ORGANIZATION",
+    "3": "B-PERSON",
+    "4": "I-LOCATION",
+    "5": "I-MISCELLANEOUS",
+    "6": "I-ORGANIZATION",
+    "7": "I-PERSON",
+    "8": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOCATION": 0,
+    "B-MISCELLANEOUS": 1,
+    "B-ORGANIZATION": 2,
+    "B-PERSON": 3,
+    "I-LOCATION": 4,
+    "I-MISCELLANEOUS": 5,
+    "I-ORGANIZATION": 6,
+    "I-PERSON": 7,
+    "O": 8
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 62000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88bc614905a1f337a3b97190636dff75420d66b6b71a76c382ea5cfa8e0a381e
+size 532365681

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "name_or_path": "NlpHUST/electra-base-vn",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}