Upload folder using huggingface_hub

README.md

@@ -0,0 +1,46 @@
+---
+language: en
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+  - sentiment-analysis
+  - imdb
+  - text-classification
+widget:
+  - text: "This movie was absolutely fantastic! Best film I've seen all year."
+---
+
+# BERT Fine-tuned on IMDB for Sentiment Analysis
+
+Fine-tuned from `bert-base-uncased` on the Stanford IMDB dataset for binary sentiment classification.
+
+## Training Details
+
+| Parameter | Value |
+|-----------|-------|
+| Base model | bert-base-uncased |
+| Learning rate | 2e-5 |
+| Batch size | 4 |
+| Epochs | 2 |
+| Max sequence length | 512 |
+
+## Usage
+
+```python
+from transformers import BertForSequenceClassification, BertTokenizer
+
+tokenizer = BertTokenizer.from_pretrained("COMP6713bert/imdb-bert-sentiment")
+model = BertForSequenceClassification.from_pretrained("COMP6713bert/imdb-bert-sentiment")
+
+inputs = tokenizer("This movie was great!", return_tensors="pt", truncation=True, max_length=512)
+with torch.no_grad():
+    outputs = model(**inputs)
+    predicted = torch.argmax(outputs.logits, dim=-1).item()
+
+print("Positive" if predicted == 1 else "Negative")
+```
+
+## Labels
+
+- 0: Negative
+- 1: Positive

config.json

@@ -0,0 +1,31 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "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-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": "single_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.3",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34ee7fe8c6d359f23d9d17fe9cda0de8e2a7829f926bba4cc92613d0d73378a
+size 437958624

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": 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]"
+}