Update app.py

app.py

@@ -110,7 +110,7 @@ def engine(input_embeds):
             batch_input_embeds = input_embeds[start:start+batch_size]
             outputs = m.generate(
                 inputs_embeds = batch_input_embeds.to("cuda"),
-                max_new_tokens = 512,
+                max_new_tokens = 16,
                 do_sample = True,
                 temperature = 0.6,
                 top_p = 0.9,
@@ -126,7 +126,7 @@ def chat_engine(input_ids):
     with torch.no_grad():
         outputs = m.generate(
             input_ids = input_ids.to("cuda"),
-            max_new_tokens = 64,
+            max_new_tokens = 512,
             do_sample = True,
             temperature = 0.6,
             top_p = 0.9,