Upload 9 files

.gitattributes

@@ -25,7 +25,6 @@
 *.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

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+datasets:
+- AyoubChLin/CNN_News_Articles_2011-2022
+language:
+- en
+metrics:
+- accuracy
+pipeline_tag: text-classification
+tags:
+- news classification
+widget:
+- text: money in the pocket
+- text: no one can win this cup in quatar..
+---
+# Fine-Tuned BART Model for Text Classification on CNN News Articles
+
+
+This is a fine-tuned BART (Bidirectional and Auto-Regressive Transformers) model for text classification on CNN news articles. The model was fine-tuned on a dataset of CNN news articles with labels indicating the article topic, using a batch size of 32, learning rate of 6e-5, and trained for one epoch.
+
+## How to Use
+
+### Install
+
+```bash
+pip install transformers
+```
+
+### Example Usage
+
+```python 
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+tokenizer = AutoTokenizer.from_pretrained("IT-community/BART_cnn_news_text_classification")
+model = AutoModelForSequenceClassification.from_pretrained("IT-community/BART_cnn_news_text_classification")
+
+# Tokenize input text
+text = "This is an example CNN news article about politics."
+inputs = tokenizer(text, padding=True, truncation=True, max_length=512, return_tensors="pt")
+
+# Make prediction
+outputs = model(inputs["input_ids"], attention_mask=inputs["attention_mask"])
+predicted_label = torch.argmax(outputs.logits)
+
+print(predicted_label)
+```
+## Evaluation
+
+The model achieved the following performance metrics on the test set:
+
+Accuracy: 0.9591836734693877
+
+F1-score: 0.958301875401112
+
+Recall: 0.9591836734693877
+
+Precision: 0.9579673040369542
+
+
+## About Us
+
+We are a scientific club from Saad Dahleb Blida University named IT Community, created in 2016 by students. We are interested in all IT fields,
+ This work was done by IT Community Club.
+
+### Contributions
+
+[Cherguelaine Ayoub](https://huggingface.co/AyoubChLin):
+
+  - Added preprocessing code for CNN news articles 
+
+  - Improved model performance with additional fine-tuning on a larger dataset 

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "ModelTC/bart-base-mnli",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "finetuning_task": "mnli",
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "business",
+    "1": "entertainment",
+    "2": "health",
+    "3": "news",
+    "4": "politics",
+    "5": "sport"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "business": 0,
+    "entertainment": 1,
+    "health": 2,
+    "news": 3,
+    "politics": 4,
+    "sport": 5
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de593ead7b6f63572ead1ddbf19fc10ff7160670e44472e6fffaab205db74585
+size 560151849

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 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}