Update app.py

app.py

@@ -41,13 +41,14 @@ def multimodal_prompt(user_input, system_prompt="You are an expert medical analy
     return response_text
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
+model_name = "OpenLLM-France/Claire-Mistral-7B-0.1"
 
-base_model_id = "OpenLLM-France/Claire-Mistral-7B-0.1"
-
-tokenizer = AutoTokenizer.from_pretrained("OpenLLM-France/Claire-Mistral-7B-0.1", trust_remote_code=True, padding_side="left")
-tokenizer.pad_token = tokenizer.eos_token
-tokenizer.padding_side = 'left'
-model = AutoModelForCausalLM.from_pretrained("OpenLLM-France/Claire-Mistral-7B-0.1")
+tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)
+model = transformers.AutoModelForCausalLM.from_pretrained(model_name,
+    device_map="auto",
+    torch_dtype=torch.bfloat16,
+    load_in_4bit=True                          # For efficient inference, if supported by the GPU card
+)
 
 class ChatBot:
     def __init__(self):