Update README.md

README.md

@@ -6,20 +6,10 @@
 ```
 import torch
 from transformers import AutoModelForSequenceClassification, AutoTokenizer, BitsAndBytesConfig
-from pathlib import Path
-import psutil
-
-def get_memory_usage():
-    process = psutil.Process()
-    memory_info = process.memory_info()
-    return memory_info.rss / 1024**2  # Convert to MB
 
 def load_and_compute_scores_with_quantized_model(model_path):
-    model_name = "BAAI/bge-reranker-v2-m3"
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    
-    bnb_config = BitsAndBytesConfig(load_in_8bit=True)
-    model = AutoModelForSequenceClassification.from_pretrained(model_path, config=bnb_config)
+    tokenizer = AutoTokenizer.from_pretrained(model_path)
+    model = AutoModelForSequenceClassification.from_pretrained(model_path)
 
     def compute_score(pairs):
         inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt')
@@ -27,12 +17,9 @@ def load_and_compute_scores_with_quantized_model(model_path):
             outputs = model(**inputs)
         return outputs.logits
 
-    after_load_memory = get_memory_usage()
-    print(f"Memory Usage after loading model: {after_load_memory:.2f} MB")
-
     scores = compute_score([['what is panda?', 'hi'], ['what is panda?', 'The giant panda (Ailuropoda melanoleuca), sometimes called a panda bear or simply panda, is a bear species endemic to China.']])
     print("Scores:", scores)
 
 quantized_model_path = "quantized_bge_reranker_v2_m3"
-load_and_compute_scores_with_quantized_model(Path(quantized_model_path))
+load_and_compute_scores_with_quantized_model(quantized_model_path)
 ```