Upload 8 files

README.md

@@ -0,0 +1,69 @@
+---
+pipeline_tag: token-classification
+tags:
+- code
+license: apache-2.0
+datasets:
+- Alex123321/english_cefr_dataset
+language:
+- en
+metrics:
+- accuracy
+library_name: transformers
+---
+# Model Card: BERT-based CEFR Classifier
+
+## Overview
+
+This repository contains a model trained to predict Common European Framework of Reference (CEFR) levels for a given text using a BERT-based model architecture. The model was fine-tuned on the CEFR dataset, and the `bert-base-...` pre-trained model was used as the base.
+
+## Model Details
+
+- Model architecture: BERT (base model: `bert-base-...`)
+- Task: CEFR level prediction for text classification
+- Training dataset: CEFR dataset
+- Fine-tuning: Epochs, Loss, etc.
+
+## Performance
+
+The model's performance during training is summarized below:
+
+
+| Epoch | Training Loss | Validation Loss |
+|-------|---------------|-----------------|
+| 1     | 0.412300      | 0.396337        |
+| 2     | 0.369600      | 0.388866        |
+| 3     | 0.298200      | 0.419018        |
+| 4     | 0.214500      | 0.481886        |
+| 5     | 0.148300      | 0.557343        |
+
+--Additional metrics:
+
+--Training Loss: 0.2900624789151278
+--Training Runtime: 5168.3962 seconds
+--Training Samples per Second: 10.642
+--Total Floating Point Operations: 1.447162776576e+16
+
+## Usage
+
+1. Install the required libraries by running `pip install transformers`.
+2. Load the trained model and use it for CEFR level prediction.
+
+
+from transformers import pipeline
+
+# Load the model
+model_name = "AbdulSami/bert-base-cased-cefr"
+
+classifier = pipeline("text-classification", model=model_name)
+
+# Text for prediction
+text = "This is a sample text for CEFR classification."
+
+# Predict CEFR level
+predictions = classifier(text)
+
+# Print the predictions
+print(predictions)
+
+

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "A1",
+    "1": "A2",
+    "2": "B1",
+    "3": "B2",
+    "4": "C1",
+    "5": "C2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "A1": 0,
+    "A2": 1,
+    "B1": 2,
+    "B2": 3,
+    "C1": 4,
+    "C2": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

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 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args .bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb9f07591dac1a3d3595b59c1a5fe79dd94c04fdf86b50f7e064b5862a58b45b
+size 3963