Upload high-accuracy IMDB sentiment RoBERTa artifacts

README.md

@@ -0,0 +1,43 @@
+---
+license: mit
+language:
+- en
+tags:
+- sentiment-analysis
+- imdb
+- roberta
+- text-classification
+pipeline_tag: text-classification
+base_model: textattack/roberta-base-imdb
+---
+
+# IMDB Sentiment RoBERTa
+
+This repository contains a high-accuracy IMDB sentiment classifier for the 2026 machine learning course task.
+
+The model is based on `textattack/roberta-base-imdb`, a RoBERTa sequence-classification model fine-tuned for IMDB sentiment analysis.
+
+## Evaluation
+
+- Dataset: `imdb_top_500.csv`
+- Accuracy: 98.40%
+- Correct: 492 / 500
+- Required minimum accuracy: 0.92
+- Labels: `0 = negative`, `1 = positive`
+
+## Usage
+
+```python
+from transformers import pipeline
+
+classifier = pipeline(
+    "sentiment-analysis",
+    model="ceilf6/imdb-sentiment-roberta",
+    tokenizer="ceilf6/imdb-sentiment-roberta",
+)
+print(classifier("This movie is great and deeply moving."))
+```
+
+## CI/CD
+
+GitHub Actions evaluates the model and uploads this repository only when accuracy is at least `0.92`.

config.json

@@ -0,0 +1,30 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "finetuning_task": "imdb",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.8.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

metrics.json

@@ -0,0 +1,43 @@
+{
+  "repo_id": "ceilf6/imdb-sentiment-roberta",
+  "source_model_id": "textattack/roberta-base-imdb",
+  "generated_at": "2026-05-15T13:45:52.977900+00:00",
+  "dataset": "data/imdb_top_500.csv",
+  "total": 500,
+  "correct": 492,
+  "accuracy": 0.984,
+  "min_accuracy": 0.92,
+  "max_length": 512,
+  "batch_size": 8,
+  "label_mapping": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "classification_report": {
+    "negative": {
+      "precision": 0.984,
+      "recall": 0.984,
+      "f1-score": 0.984,
+      "support": 250.0
+    },
+    "positive": {
+      "precision": 0.984,
+      "recall": 0.984,
+      "f1-score": 0.984,
+      "support": 250.0
+    },
+    "accuracy": 0.984,
+    "macro avg": {
+      "precision": 0.984,
+      "recall": 0.984,
+      "f1-score": 0.984,
+      "support": 500.0
+    },
+    "weighted avg": {
+      "precision": 0.984,
+      "recall": 0.984,
+      "f1-score": 0.984,
+      "support": 500.0
+    }
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:982b2f974f44c79dda9a108633cc225cc081b6e2dbc1364bbcfe37a7708cafd4
+size 498612824

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}