Updated

main.py

@@ -20,7 +20,7 @@ from transformers import pipeline
 # CONFIGURATION
 # ===============================================
 API_SECRET = "techdisciplesai404"
-MODEL_NAME = "google/flan-t5-large" #meta-llama/Llama-2-13b-chat-hf
+MODEL_NAME = "meta-llama/Llama-2-13b-chat-hf"
 DEVICE = 0 if torch.cuda.is_available() else -1
 
 # ===============================================
@@ -42,13 +42,12 @@ try:
 
 
     hf_pipeline = pipeline(
-        "text2text-generation", #text-generation-inference
+        "text-generation-inference",
         model=MODEL_NAME,
         device=DEVICE,
         max_new_tokens=1024,  
-        temperature=0.4,      
+        temperature=0.7,      
         do_sample=True,       
-        repetition_penalty=1.2 
     )