Upload trained BERT CEFR classifier - roberta-base

README.md

@@ -0,0 +1,46 @@
+---
+  language: en
+  tags:
+  - text-classification
+  - cefr
+  - education
+  license: mit
+  ---
+
+  # CEFR Text Classifier
+
+  This model classifies English text by CEFR level (A1, A2, B1, B2, C1/C2).
+
+  ## Model Details
+  - Base Model: roberta-base
+  - Task: Multi-class text classification (5 classes)
+  - Training Data: 100k samples
+
+  ## Performance
+  - In-Domain Test Accuracy: 0.9817
+  - In-Domain QWK: 0.9908
+  - Out-of-Domain Test Accuracy: 0.2543
+  - Out-of-Domain QWK: 0.3367
+
+  ## Usage
+  ```python
+  from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+  tokenizer = AutoTokenizer.from_pretrained("theluantran/cefr-bert-classifier")
+  model = AutoModelForSequenceClassification.from_pretrained("theluantran/cefr-bert-classifier")
+
+  text = "Your text here"
+  inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
+  outputs = model(**inputs)
+  predictions = outputs.logits.argmax(-1)
+
+  label_map = {0: 'A1', 1: 'A2', 2: 'B1', 3: 'B2', 4: 'C1/C2'}
+  predicted_level = label_map[predictions.item()]
+  ```
+
+  ## Training Configuration
+  - Epochs: 4
+  - Batch Size: 16
+  - Learning Rate: 2e-05
+  - Max Length: 512
+  

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18eb344f8d6476fe5583c64995ae6819e0898f74db6ac72dee387a70d1236e69
+size 498622052

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_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "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>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb34d301c5b6affb3edd6fc1e9106a4280f711054eea889cec149e6862a54ac8
+size 5841