Update app.py

app.py

@@ -2,13 +2,13 @@ import streamlit as st
 import logging
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-# Set logging verbosity to CRITICAL to reduce noise
-logging.set_verbosity(logging.CRITICAL)
+# Set the logger to display only CRITICAL messages
+logging.basicConfig(level=logging.CRITICAL)
 
 # Cache the model and tokenizer to avoid reloading it every time
 @st.cache(allow_output_mutation=True, suppress_st_warning=True)
 def load_model():
-    model_name = "Abbeite/chest_and_physical_limitations2"  # Replace with your model name
+    model_name = "your-model-name"  # Replace with your actual model name
     tokenizer = AutoTokenizer.from_pretrained(model_name)
     model = AutoModelForCausalLM.from_pretrained(model_name)
     return model, tokenizer
@@ -17,8 +17,8 @@ model, tokenizer = load_model()
 
 # Function to generate text with the model
 def generate_text(prompt):
-    formatted_prompt = f"[INST] {prompt} [/INST]"  # Format the prompt
-    pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=500)
+    formatted_prompt = f"[INST] {prompt} [/INST]"  # Format the prompt according to your specification
+    pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_length=500)
     result = pipe(formatted_prompt)
     return result[0]['generated_text']