Update app.py

app.py

@@ -8,7 +8,7 @@ from html import escape
 # Model config
 PRIMARY_MODEL = "Smilyai-labs/Sam-reason-A1"
 FALLBACK_MODEL = "Smilyai-labs/Sam-reason-S2.1"
-USAGE_LIMIT = 2
+USAGE_LIMIT = 5
 RESET_AFTER_SECONDS = 20 * 60  # 20 minutes
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
@@ -27,7 +27,7 @@ def load_models():
     return f"✅ Loaded: {PRIMARY_MODEL} with fallback {FALLBACK_MODEL}"
 
 # Token streaming
-def generate_stream(prompt, use_fallback=False, max_length=10, temperature=0.6, top_p=0.9):
+def generate_stream(prompt, use_fallback=False, max_length=100, temperature=0.2, top_p=0.9):
     model = fallback_model if use_fallback else primary_model
     tokenizer = fallback_tokenizer if use_fallback else primary_tokenizer
     input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)