Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,81 @@
+
+  - email-classification
+  - text-classification
+language: en
+license: apache-2.0
+datasets:
+  - Tobi-Bueck/customer-support-tickets
+metrics:
+  - accuracy
+model_type: xlm-roberta
+pipeline_tag: text-classification
+---
+
+#  xlm-roberta-email-classifier
+
+Fine-tuned version of `xlm-roberta-base` for multi-class classification of English-language emails.  
+This model is designed to automatically route or tag incoming messages based on their content.
+
+##  Model Overview
+
+- **Base Model**: `xlm-roberta-base`
+- **Task**: Email classification (10 categories)
+- **Language**: English
+- **Frameworks**: Hugging Face Transformers, PyTorch Lightning
+- **Training Tracker**: Weights & Biases
+
+##  Performance
+
+- Accuracy: 0.42  
+- F1 Score: 0.436  
+- Precision: 0.527  
+- Recall: 0.42  
+
+## Class Labels
+
+The model predicts one of the following categories:
+
+| Label ID | Category                        |
+|----------|---------------------------------|
+| 0        | Billing and Payments            |
+| 1        | Customer Service                |
+| 2        | General Inquiry                 |
+| 3        | Human Resources                 |
+| 4        | IT Support                      |
+| 5        | Product Support                 |
+| 6        | Returns and Exchanges           |
+| 7        | Sales and Pre-Sales             | 
+| 8        | Service Outages and Maintenance |
+| 9        | Technical Support               | 
+
+
+##  Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+tokenizer = AutoTokenizer.from_pretrained("ale-dp/xlm-roberta-email-classifier")
+model = AutoModelForSequenceClassification.from_pretrained("ale-dp/xlm-roberta-email-classifier")
+
+email_text = "I'd like to return the item I purchased last week."
+inputs = tokenizer(email_text, return_tensors="pt")
+outputs = model(**inputs)
+
+predicted_class_id = outputs.logits.argmax().item()
+label_map = {
+    'Billing and Payments': 0,
+    'Customer Service': 1,
+    'General Inquiry': 2,
+    'Human Resources': 3,
+    'IT Support': 4,
+    'Product Support': 5,
+    'Returns and Exchanges': 6,
+    'Sales and Pre-Sales': 7,
+    'Service Outages and Maintenance': 8,
+    'Technical Support': 9
+}
+predicted_label = list(label_map.keys())[list(label_map.values()).index(predicted_class_id)]
+print(predicted_label)
+```
+
+

config.json

@@ -0,0 +1,52 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a113f765a1f539126e057149b79e1e0e32d85c90ffed982ff1a4a9d12d2b84b
+size 1112229616

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e2236a9938d0d23f6f654386b99a9f79f7b9555c3d5f42924cb3a168a0f3811
+size 5713