Update README.md

README.md

@@ -18,28 +18,30 @@ This model was trained using AutoTrain. For more information, please visit [Auto
 
 # Usage
 
-```python
+```bash
+pip install peft
+```
 
+```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import AutoPeftModelForCausalLM, PeftConfig
 
-model_path = "Aryan-401/phi-3-mini-4k-instruct-finetune-guanaco"
+model_id = "Aryan-401/phi-3-mini-4k-instruct-finetune-guanaco"
+peft_model=AutoPeftModelForCausalLM.from_pretrained(model_id)
 
-tokenizer = AutoTokenizer.from_pretrained(model_path)
-model = AutoModelForCausalLM.from_pretrained(
-    model_path,
-    device_map="auto",
-    torch_dtype='auto'
-).eval()
+model = peft_model.merge_and_unload()
+tokenizer = AutoTokenizer.from_pretrained(model_id)
 
-# Prompt content: "hi"
 messages = [
-    {"role": "user", "content": "hi"}
+    {"role": "user", "content": "What is the Value of Pi?"}
 ]
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+model = model.to(device).eval()
 
 input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
-output_ids = model.generate(input_ids.to('cuda'))
+output_ids = model.generate(input_ids.to(device), max_length= 1000)
 response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
 
-# Model response: "Hello! How can I assist you today?"
 print(response)
 ```