Modify Downstream Usage

README.md

@@ -88,11 +88,12 @@ print(response['choices'][0]['text'].strip())
 <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
 
 ```python
+# USING ON GPU MACHINE
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel, PeftConfig
 
-model_name = "microsoft/phi-2"
+model_name = "pavankumarbalijepalli/phi2-sqlcoder"
 
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
@@ -101,12 +102,10 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
-inputs = tokenizer(new_prompt, return_tensors="pt", padding=True, truncation=True)
+inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True)
 inputs.to('cuda')
 
-model_id = "pavankumarbalijepalli/phi2-sqlcoder"
-trained_model = PeftModel.from_pretrained(model, model_id)
-outputs = trained_model.generate(**inputs, max_length=1000)
+outputs = model.generate(**inputs, max_length=1000)
 text = tokenizer.batch_decode(outputs,skip_special_tokens=True)[0]
 print(text)
 ```