Update README.md

README.md

@@ -74,15 +74,22 @@ Usage:
     #Load base model weight & tokenizer
     tokenizer = AutoTokenizer.from_pretrained(tokenizer_name,trust_remote_code=True)
   
-    model = AutoModelForCausalLM.from_pretrained(model_name, device_map='auto', trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(basemodel_name, device_map='auto', trust_remote_code=True)
     
     #Load adapter
     fine_tuned_model = PeftModel.from_pretrained(model, model_id)
-  
+    
+    # Tokenize
+    inputs = tokenizer(prompt, 
+                   return_tensors="pt",
+                   return_attention_mask=True,
+                   padding=False, 
+                   truncation=True)
     #Run inference    
     outputs = fine_tuned_model.generate(**inputs, max_length=1000)
     
-    text = tokenizer.batch_decode(outputs,skip_special_tokens=True)[0]
+    # Decode output
+    text = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
     print(text)
     
 Usage (with quantization):