Updated tokenizer & fixed sentiment labels

New Text Document.txt

@@ -0,0 +1,12 @@
+from transformers import pipeline
+
+# Load the model from Hugging Face
+model_name = "DilipKY/my-text-classifier"  # Ensure this matches your model name
+classifier = pipeline("text-classification", model=model_name)
+
+# Test with a sample text
+sample_text = "This movie was amazing! The plot was so engaging and the acting was superb."
+result = classifier(sample_text)
+
+# Print the output
+print(result)

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

test_model.py

@@ -1,16 +1,20 @@
 from transformers import pipeline, AutoTokenizer
 
+# Load model
 model_name = "DilipKY/my-text-classifier"
-tokenizer_name = "bert-base-uncased"  # Use "bert-base-cased" if your model is case-sensitive
-
-# Load the correct tokenizer
-tokenizer = AutoTokenizer.from_pretrained(tokenizer_name)
-
-# Load the model with the tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 classifier = pipeline("text-classification", model=model_name, tokenizer=tokenizer)
 
-# Test the model
-sample_text = "I love this product! It's amazing."
+# Label mapping (adjust if necessary)
+label_map = {"LABEL_0": "NEGATIVE", "LABEL_1": "POSITIVE"}
+
+# Test with input text
+sample_text = "I love this movie!"
 result = classifier(sample_text)
 
+# Convert label
+result[0]['label'] = label_map.get(result[0]['label'], result[0]['label'])
+
+# Print the result
+print("\n🔍 Sentiment Classification Result:")
 print(result)

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}