Update app.py

app.py

@@ -7,12 +7,18 @@ import torch
 # Load the model and tokenizer
 @st.cache_resource
 def load_model():
-    model = AutoModelForCausalLM.from_pretrained(
-        "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
-        device_map="auto",
-        torch_dtype=torch.float16,
-        load_in_8bit=True,  # Enable 8-bit quantization
-    )
+    # model = AutoModelForCausalLM.from_pretrained(
+    #     "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
+    #     device_map="auto",
+    #     torch_dtype=torch.float16,
+    #     load_in_8bit=True,  # Enable 8-bit quantization
+    # )
+    model_name = "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ"
+    model = AutoModelForCausalLM.from_pretrained(model_name,
+                                             device_map="auto",
+                                             trust_remote_code=False,
+                                             revision="main")
+
     tokenizer = AutoTokenizer.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.2-GPTQ")
     config = PeftConfig.from_pretrained("vignesh0007/Hubermangpt")
     model = PeftModel.from_pretrained(model, "vignesh0007/Hubermangpt")