Update app.py

app.py

@@ -8,7 +8,7 @@ from threading import Thread
 
 # Loading the tokenizer and model from Hugging Face's model hub.
 tokenizer = AutoTokenizer.from_pretrained("soketlabs/pragna-1b", token=os.environ.get('HF_TOKEN'))
-model = AutoModelForCausalLM.from_pretrained("soketlabs/pragna-1b", token=os.environ.get('HF_TOKEN'))
+model = AutoModelForCausalLM.from_pretrained("soketlabs/pragna-1b-it-v0.1", token=os.environ.get('HF_TOKEN'))
 
 # using CUDA for an optimal experience
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
@@ -38,7 +38,7 @@ def predict(message, history):
     generate_kwargs = dict(
         model_inputs,
         streamer=streamer,
-        max_new_tokens=50,
+        max_new_tokens=300,
         do_sample=True,
         top_p=0.95,
         top_k=50,