Adding ONNX file of this model (#6)

- Adding ONNX file of this model (a49525de74e3567169157cb8ff78fa95ad144823)


Co-authored-by: Ali Cenk Baytop <alicenkbaytop@users.noreply.huggingface.co>

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -6,10 +6,20 @@ widget:
 - text: "My name is jean-baptiste and I live in montreal"
 - text: "My name is clara and I live in berkeley, california."
 - text: "My name is wolfgang and I live in berlin"
+train-eval-index:
+- config: conll2003
+  task: token-classification
+  task_id: entity_extraction
+  splits:
+    eval_split: validation
+  col_mapping:
+    tokens: tokens
+    ner_tags: tags
+license: mit
 
 ---
 
-# roberta-large-ner: model fine-tuned from roberta-large for NER task
+# roberta-large-ner-english: model fine-tuned from roberta-large for NER task
 
 ## Introduction
 
@@ -37,15 +47,15 @@ Train | Validation
 -|-
 17494 | 3250
 
-## How to use camembert-ner with HuggingFace
+## How to use roberta-large-ner-english with HuggingFace
 
-##### Load camembert-ner and its sub-word tokenizer :
+##### Load roberta-large-ner-english and its sub-word tokenizer :
 
 ```python
 from transformers import AutoTokenizer, AutoModelForTokenClassification
 
-tokenizer = AutoTokenizer.from_pretrained("Jean-Baptiste/roberta-large-ner")
-model = AutoModelForTokenClassification.from_pretrained("Jean-Baptiste/roberta-large-ner")
+tokenizer = AutoTokenizer.from_pretrained("Jean-Baptiste/roberta-large-ner-english")
+model = AutoModelForTokenClassification.from_pretrained("Jean-Baptiste/roberta-large-ner-english")
 
 
 ##### Process text sample (from wikipedia)
@@ -119,3 +129,6 @@ ORG|0.7655|0.6437|0.6993
 LOC|0.8727|0.6180|0.7236
 
 
+
+For those who could be interested, here is a short article on how I used the results of this model to train a LSTM model for signature detection in emails:
+https://medium.com/@jean-baptiste.polle/lstm-model-for-email-signature-detection-8e990384fefa

config.json

@@ -12,19 +12,19 @@
   "hidden_size": 1024,
   "id2label": {
     "0": "O",
-    "1": "LOC",
-    "2": "PER",
-    "3": "MISC",
-    "4": "ORG"
+    "1": "PER",
+    "2": "ORG",
+    "3": "LOC",
+    "4": "MISC"
   },
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "label2id": {
-    "LOC": 1,
-    "MISC": 3,
+    "LOC": 3,
+    "MISC": 4,
     "O": 0,
-    "ORG": 4,
-    "PER": 2
+    "ORG": 2,
+    "PER": 1
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,

results.csv

@@ -1,6 +1,6 @@
 ,precision,recall,f1,entity
-0,0.9795249795249795,0.9862561847168774,0.9828790576633339,LOC
-1,0.9914318668643928,0.9927404718693285,0.9920857378400659,PER
-2,0.9292274446245273,0.9262250942380184,0.9277238403451995,MISC
-3,0.9627007895453308,0.966120218579235,0.9644074730669576,ORG
-4,0.9740825890497252,0.9766692954784437,0.9753719894698967,Overall
+0,0.9904511030622325,0.9925754825936314,0.9915121549237741,PER
+1,0.9628323385784048,0.969672131147541,0.966240130683365,ORG
+2,0.974924221548636,0.9725123694337549,0.9737168019815605,LOC
+3,0.9308278867102396,0.9203015616585891,0.925534795559166,MISC
+4,0.9728188879121981,0.9734490010515248,0.9731265700746845,Overall