Update README.md

README.md

@@ -48,32 +48,7 @@ To improve inference efficiency, models were converted to FP16:
 import torch
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
 
-# List of fine-tuned models
-models = [
-    "fine_tuned_models/en-mr/final/", 
-    "fine_tuned_models/es-pt/final/", 
-    "fine_tuned_models/eo-nl/final/", 
-    "fine_tuned_models/en-mr/final/"
-]
-
-output_fp16_dir = "fine_tuned_models_fp16"
-
-# Convert each model to FP16
-for model_path in models:
-    print(f"Quantizing {model_path} to FP16...")
-    
-    # Load model and tokenizer
-    model = AutoModelForSeq2SeqLM.from_pretrained(model_path, torch_dtype=torch.float16)
-    tokenizer = AutoTokenizer.from_pretrained(model_path)
-
-    # Define save path
-    save_path = model_path.replace("fine_tuned_models", output_fp16_dir)
-    
-    # Save quantized model
-    model.save_pretrained(save_path)
-    tokenizer.save_pretrained(save_path)
-
-    print(f"Saved quantized model to: {save_path}\n")
+
 
 # Inference Example
 ```