Update app.py

app.py

@@ -30,7 +30,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
-model_id = "prithivMLmods/Llama-Express.1"
+model_id = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
@@ -58,7 +58,7 @@ def generate(
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
     input_ids = input_ids.to(model.device)
 
-    streamer = TextIteratorStreamer(tokenizer, timeout=40.0, skip_prompt=True, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, timeout=20.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         {"input_ids": input_ids},
         streamer=streamer,