Update README.md

README.md

@@ -45,7 +45,7 @@ import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
 
-# --- 1. Load Model & Adapter (Your Requested Format) ---
+#  1. Load Model & Adapter 
 base_model = "google/gemma-2b"
 adapter_repo = "indrajeet77/sentiment-analyzer"
 
@@ -60,7 +60,7 @@ model = AutoModelForCausalLM.from_pretrained(
 model = PeftModel.from_pretrained(model, adapter_repo)
 
 
-# --- 2. Inference Function (Fixes the "repetition" issue) ---
+#  2. Inference Function 
 def get_sentiment(text):
     # We use "Few-Shot Prompting" to force the model to give a one-word answer
     prompt = f"""Classify the sentiment as positive, negative, or neutral.
@@ -88,7 +88,7 @@ Sentiment:"""
     response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
     return response.strip().lower()
 
-# --- 3. Run It ---
+#  3. Run It 
 print("Model Loaded. Testing...")
 text = "The product quality is amazing"
 print(f"Text: {text}")