Update app.py

app.py

@@ -1,12 +1,23 @@
 from transformers import AutoTokenizer, AutoModelForCausalLM
 from peft import LoraConfig, get_peft_model
 import torch
- 
-# Load the tokenizer and model
+
+
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM
+
+config = PeftConfig.from_pretrained("youssef227/llama-3-8b-Instruct-bnb-telcom-3")
 print("step 1 ")
-tokenizer = AutoTokenizer.from_pretrained("youssef227/llama-3-8b-Instruct-bnb-telcom-3")
-print("step 2 ")
-model = AutoModelForCausalLM.from_pretrained("youssef227/llama-3-8b-Instruct-bnb-telcom-3")
+base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-Instruct-bnb-4bit")
+print("step 2")
+model = PeftModel.from_pretrained(base_model, "youssef227/llama-3-8b-Instruct-bnb-telcom-3")
+print("step 3")
+
+# Load the tokenizer and model
+# print("step 1 ")
+# tokenizer = AutoTokenizer.from_pretrained("youssef227/llama-3-8b-Instruct-bnb-telcom-3")
+# print("step 2 ")
+# model = AutoModelForCausalLM.from_pretrained("youssef227/llama-3-8b-Instruct-bnb-telcom-3")
 def generator(text):
   inputs = tokenizer(
   [