final commits

app.py

@@ -0,0 +1,22 @@
+import torch
+import gradio as gr
+from utils import *
+from torch import nn
+import lightning.pytorch as pl
+from torch.nn import functional as F
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+
+demo = gr.Interface(
+    fn=generate_context,
+    inputs=[
+        gr.Textbox("Once Upon a Time ...", label="Enter Prompt to continue generation"),
+        gr.Slider(0.7, 1, value=0.8, label="Temperature", info="Parameter to controls the level of randomness in the sampling process . Higher values increases creativity",step=0.1),
+        gr.Slider(100, 300, value=200, label="Top K", info="Limit the response to K next predictions",step=50),
+        gr.Slider(10, 100, value=50, label="Max Tokens", info="Set value to get the output to max_values of tokens",step=10),
+    ],
+    outputs="text",
+    examples = examples,
+)
+
+demo.launch()

requirements.txt

@@ -0,0 +1,10 @@
+gradio
+torch 
+torchvision 
+torchaudio
+huggingface_hub 
+sentencepiece 
+tokenizers 
+lightning 
+fabric 
+jsonargparse