Create app.py

app.py

@@ -0,0 +1,20 @@
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from peft import PeftModel
+
+base_model = "ybelkada/falcon-7b-sharded-bf16"
+adapter_model = "Sanjay002/falcon-7b-mental-health-finetuned"
+
+tokenizer = AutoTokenizer.from_pretrained(base_model)
+model = AutoModelForCausalLM.from_pretrained(base_model, device_map="auto", torch_dtype=torch.float16)
+model = PeftModel.from_pretrained(model, adapter_model)
+model.eval()
+
+def chat(message):
+    inputs = tokenizer(message, return_tensors="pt").to("cuda")
+    outputs = model.generate(**inputs, max_new_tokens=150, do_sample=True, temperature=0.7)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+gr.Interface(fn=chat, inputs="text", outputs="text", title="🧠 Mental Health Chatbot").queue().launch(share=False)