.

README.md

@@ -0,0 +1,20 @@
+# My Custom BERT Model
+
+This is a fine-tuned version of `bert-base-uncased` for binary sentiment analysis.
+
+## Model Overview
+- Model: BERT for sequence classification
+- Number of Labels: 2
+- Dataset: Custom sentiment dataset
+
+## How to Use
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+# Load model and tokenizer
+model = AutoModelForSequenceClassification.from_pretrained("your_username/my_model")
+tokenizer = AutoTokenizer.from_pretrained("your_username/my_model")
+
+# Tokenize text
+inputs = tokenizer("I love this!", return_tensors="pt")
+outputs = model(**inputs)

config.json

@@ -0,0 +1,13 @@
+{
+  "architectures": ["BertForSequenceClassification"],
+  "hidden_size": 768,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "vocab_size": 30522,
+  "type_vocab_size": 2,
+  "max_position_embeddings": 512,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-12,
+  "hidden_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0.1
+}

pytorch_model.bin

@@ -0,0 +1,9 @@
+from transformers import BertForSequenceClassification, BertTokenizer
+
+# Initialize model and tokenizer
+model = BertForSequenceClassification.from_pretrained("bert-base-uncased", num_labels=2)
+tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")
+
+# Save model weights and tokenizer
+model.save_pretrained("./my_model")
+tokenizer.save_pretrained("./my_model")

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "cls_token": "[CLS]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer.json

@@ -0,0 +1,4 @@
+{
+  "do_lower_case": true,
+  "max_len": 512
+}