Update app.py

app.py

@@ -1,14 +1,19 @@
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig
 from peft import PeftModel, PeftConfig
 
 model_name = "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ"
+
+configm = AutoConfig.from_pretrained(model_name)
+configm.quantization_config["disable_exllama"] = True
+
 model = AutoModelForCausalLM.from_pretrained(model_name,
                                              trust_remote_code=False,
                                              revision="main",
+                                             config=configm
                                              )
 
 config = PeftConfig.from_pretrained("saanvi-bot/jayson")
-model = PeftModel.from_pretrained(model, "saanvi-bot/jayson")
+model = PeftModel.from_pretrained(model, "saanvi-bot/jayson", peft_config = config)
 
 # load tokenizer
 tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)