Update app.py

app.py

@@ -1,23 +1,15 @@
 import gradio as gr
 import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
-from peft import PeftModel
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel, PeftConfig
 
 base_model = "mistralai/Mistral-7B-v0.1"
 
-bnb_config = BitsAndBytesConfig(
-    load_in_4bit= True,
-    bnb_4bit_quant_type= "nf4",
-    bnb_4bit_compute_dtype= torch.bfloat16,
-    bnb_4bit_use_double_quant= False,
-)
-model = AutoModelForCausalLM.from_pretrained(
-    base_model,
-    quantization_config=bnb_config,
-    device_map={"": 0}
-)
+config = PeftConfig.from_pretrained("kiki7sun/mixtral-academic-finetune0119")
+model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
+ft_model = PeftModel.from_pretrained(model, "kiki7sun/mixtral-academic-finetune0119")
 
-ft_model = PeftModel.from_pretrained(model, 'kiki7sun/mixtral-academic-finetune-QLoRA-0121')
+# ft_model = PeftModel.from_pretrained(model, 'kiki7sun/mixtral-academic-finetune-QLoRA-0121')
 
 tokenizer = AutoTokenizer.from_pretrained(
     base_model_id,
@@ -34,6 +26,10 @@ def greet(eval_prompt,max_new_tokens):
 
   return result
 
-demo = gr.Interface(fn=greet, inputs="textbox", outputs="textbox")
+demo = gr.Interface(fn=greet, 
+                    inputs="textbox", 
+                    outputs="textbox",
+                    title="My Academic Chat",
+                   )
 
 demo.queue().launch(debug=True, share=True, inline=False)