Update app.py

app.py

@@ -2,17 +2,19 @@ import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-model_id = "google/gemma-2b-it"
+model_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+
+print("⏳ Loading TinyLlama...")
 
-# Load model
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
-    torch_dtype=torch.float32,
     device_map="cpu"
 )
 
+print("✅ Model Loaded!")
+
 def generate_text(prompt):
     inputs = tokenizer(prompt, return_tensors="pt")
 
@@ -21,17 +23,18 @@ def generate_text(prompt):
             **inputs,
             max_new_tokens=120,
             temperature=0.7,
-            do_sample=True
+            do_sample=True,
+            top_p=0.9
         )
 
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-# UI
 iface = gr.Interface(
     fn=generate_text,
     inputs=gr.Textbox(lines=4, placeholder="कुछ पूछो..."),
     outputs="text",
-    title="Texly AI",
+    title="Texly AI (TinyLlama)",
+    description="Fast & Free AI Chatbot"
 )
 
 iface.launch()