Commit From AutoTrain

.gitattributes

@@ -32,3 +32,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,49 @@
+---
+tags:
+- autotrain
+- token-classification
+language:
+- unk
+widget:
+- text: "I love AutoTrain 🤗"
+datasets:
+- teacookies/autotrain-data-20-12-2022_general_info_exam
+co2_eq_emissions:
+  emissions: 21.038593211432406
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Entity Extraction
+- Model ID: 2543777917
+- CO2 Emissions (in grams): 21.0386
+
+## Validation Metrics
+
+- Loss: 0.007
+- Accuracy: 0.998
+- Precision: 0.937
+- Recall: 0.952
+- F1: 0.945
+
+## Usage
+
+You can use cURL to access this model:
+
+```
+$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/teacookies/autotrain-20-12-2022_general_info_exam-2543777917
+```
+
+Or Python API:
+
+```
+from transformers import AutoModelForTokenClassification, AutoTokenizer
+
+model = AutoModelForTokenClassification.from_pretrained("teacookies/autotrain-20-12-2022_general_info_exam-2543777917", use_auth_token=True)
+
+tokenizer = AutoTokenizer.from_pretrained("teacookies/autotrain-20-12-2022_general_info_exam-2543777917", use_auth_token=True)
+
+inputs = tokenizer("I love AutoTrain", return_tensors="pt")
+
+outputs = model(**inputs)
+```

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "AutoTrain",
+  "_num_labels": 17,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-tec_cert_type",
+    "1": "B-tec_expiry_date",
+    "2": "B-tec_first_issue_date",
+    "3": "B-tec_issue_date",
+    "4": "B-tec_model_no",
+    "5": "B-tec_report_no",
+    "6": "B-tec_report_type",
+    "7": "B-tec_standard",
+    "8": "I-tec_cert_type",
+    "9": "I-tec_expiry_date",
+    "10": "I-tec_first_issue_date",
+    "11": "I-tec_issue_date",
+    "12": "I-tec_model_no",
+    "13": "I-tec_report_no",
+    "14": "I-tec_report_type",
+    "15": "I-tec_standard",
+    "16": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-tec_cert_type": 0,
+    "B-tec_expiry_date": 1,
+    "B-tec_first_issue_date": 2,
+    "B-tec_issue_date": 3,
+    "B-tec_model_no": 4,
+    "B-tec_report_no": 5,
+    "B-tec_report_type": 6,
+    "B-tec_standard": 7,
+    "I-tec_cert_type": 8,
+    "I-tec_expiry_date": 9,
+    "I-tec_first_issue_date": 10,
+    "I-tec_issue_date": 11,
+    "I-tec_model_no": 12,
+    "I-tec_report_no": 13,
+    "I-tec_report_type": 14,
+    "I-tec_standard": 15,
+    "O": 16
+  },
+  "layer_norm_eps": 1e-12,
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "padding": "max_length",
+  "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": "4.22.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105879
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76a8ad38d2fbe25e4aca1d4d9dd5824aeb5c9a469cd835c1a05796e1fca1fd18
+size 667187757

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a530333648f6b969fe92eacd2b0a338cfe48fd0fb5f194b1c3ad5c85f87a95e2
+size 2563635

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "AutoTrain",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}