Update app.py

app.py

@@ -7,8 +7,8 @@ from threading import Thread
 
 # Loading the tokenizer and model from Hugging Face's model hub.
 if torch.cuda.is_available():
-    tokenizer = AutoTokenizer.from_pretrained("upstage/SOLAR-10.7B-Instruct-v1.0")
-    model = AutoModelForCausalLM.from_pretrained("upstage/SOLAR-10.7B-Instruct-v1.0", torch_dtype=torch.float16, device_map="auto")
+    tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-7B-Chat")
+    model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen1.5-7B-Chat", torch_dtype=torch.float16, device_map="auto")
 
 
 # Defining a custom stopping criteria class for the model's text generation.
@@ -41,8 +41,8 @@ def predict(message, history):
         do_sample=True,
         top_p=0.95,
         top_k=50,
-        temperature=0.2,
-        repetition_penalty=1.2,
+        temperature=0.7,
+        repetition_penalty=1.0,
         num_beams=1,
         stopping_criteria=StoppingCriteriaList([stop])
     )
@@ -58,7 +58,7 @@ def predict(message, history):
 
 # Setting up the Gradio chat interface.
 gr.ChatInterface(predict,
-                 title="SOLAR 10.7B Instruct v1.0",
+                 title="Qwen1.5 7B Chat Demo",
                  description="Warning. All answers are generated and may contain inaccurate information.",
                  examples=['How do you cook fish?', 'Who is the president of the United States?']
                  ).launch()  # Launching the web interface.