Add VakilAI model

app.py

@@ -1,14 +1,44 @@
 import gradio as gr
+import torch
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+
+BASE_MODEL = "meta-llama/Llama-3.2-3B"
+ADAPTER_MODEL = "devNaam/vakilai-llama32-3b-v1"
+
+tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL)
+
+model = AutoModelForCausalLM.from_pretrained(
+    BASE_MODEL,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+model = PeftModel.from_pretrained(model, ADAPTER_MODEL)
+
+def vakil_ai(prompt):
+
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+    output = model.generate(
+        **inputs,
+        max_new_tokens=300,
+        temperature=0.7,
+        top_p=0.9
+    )
+
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+
+    return response
 
-def greet(name):
-    return "Hello " + name + "!! Welcome to AI Vakil"
 
 demo = gr.Interface(
-    fn=greet,
-    inputs="text",
+    fn=vakil_ai,
+    inputs=gr.Textbox(lines=4, placeholder="Ask your legal question..."),
     outputs="text",
-    title="AI Vakil",
-    description="First test deployment"
+    title="AI Vakil – Legal Assistant",
+    description="VakilAI powered by Llama 3.2"
 )
 
 demo.launch()